INDEX

Explanations

statements that include the word "not" in conjunction with verbs or adjectives

oai_token-act-pair · gpt-3.5-turbo

assertions or definitive statements regarding conditions or requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Occupations

-0.64

 Rape

-0.63

OB

-0.63

arine

-0.63

$$$$

-0.62

WT

-0.61

kay

-0.61

Dest

-0.61

hart

-0.60

Cook

-0.60

POSITIVE LOGITS

 nonetheless

1.55

 nevertheless

1.33

etheless

1.04

 still

0.86

 strangely

0.85

 proble

0.80

 adamant

0.78

 persisted

0.77

 thereto

0.77

 retained

0.76

Activations Density 1.004%

statements that include the word "not" in conjunction with verbs or adjectives

assertions or definitive statements regarding conditions or requirements

No Comments

No Known Activations