INDEX

Explanations

phrases related to technology and software development, particularly involving function support and programming instances

oai_token-act-pair · gpt-3.5-turbo

specific proper nouns and keywords related to various topics or entities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

],"

-0.72

interstitial

-0.61

PsyNetMessage

-0.58

achelor

-0.55

 captcha

-0.55

)",

-0.54

 bothering

-0.54

 mouth

-0.53

 disguise

-0.53

itbart

-0.53

POSITIVE LOGITS

 meanwhile

0.79

 however

0.75

beit

0.74

 ---------

0.70

vic

0.70

sequently

0.69

ogether

0.69

udos

0.66

hetically

0.66

 refers

0.65

Activations Density 0.842%

phrases related to technology and software development, particularly involving function support and programming instances

specific proper nouns and keywords related to various topics or entities

No Comments

No Known Activations