INDEX

Explanations

words related to categorization or grouping

oai_token-act-pair · gpt-3.5-turbo

classifications and types of things

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

stocks

-0.65

¬¼

-0.64

 SHARES

-0.63

stock

-0.62

Ĥª

-0.59

tz

-0.57

"))

-0.56

ndum

-0.56

 Piper

-0.56

eting

-0.55

POSITIVE LOGITS

ils

0.64

anges

0.63

VK

0.59

ILA

0.59

ults

0.59

VK

0.58

 Victoria

0.57

 Garfield

0.57

 Kung

0.55

apeshifter

0.54

Activations Density 0.453%

words related to categorization or grouping

classifications and types of things

No Comments

No Known Activations