INDEX

Explanations

terms related to legislation or regulations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "and" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

meet

-0.61

bo

-0.59

Contents

-0.57

 Rohing

-0.55

busters

-0.54

jud

-0.53

BO

-0.53

>[

-0.52

Doug

-0.52

POSITIVE LOGITS

 consequently

1.10

 therefore

1.10

 thus

1.05

 hence

1.00

 thereby

0.91

 vice

0.84

 secondly

0.83

 THEN

0.82

 indeed

0.78

 subsequently

0.77

Activations Density 0.412%

terms related to legislation or regulations

instances of the word "and" in various contexts

No Comments

No Known Activations