INDEX

Explanations

phrases containing names of locations or people

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names related to various subjects

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

©¶æ

-0.78

PDATE

-0.73

ħĭ

-0.70

brance

-0.68

×ķ

-0.68

BIL

-0.66

FORMATION

-0.65

FontSize

-0.65

TABLE

-0.63

 dime

-0.62

POSITIVE LOGITS

urat

0.90

rays

0.81

iru

0.81

hu

0.80

iang

0.79

hai

0.78

orno

0.78

ai

0.77

ju

0.77

hua

0.76

Activations Density 0.274%

phrases containing names of locations or people

proper nouns and names related to various subjects

No Comments

No Known Activations