INDEX

Explanations

phrases indicating repetition or frequency

oai_token-act-pair · gpt-3.5-turbo

mentions of repeated actions or occurrences

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

Reviewer

-0.88

XT

-0.84

ains

-0.77

Marginal

-0.76

aceous

-0.74

ettle

-0.74

ourt

-0.73

rats

-0.73

agra

-0.72

rights

-0.72

POSITIVE LOGITS

 consecut

0.97

cale

0.86

 throughout

0.78

fold

0.75

points

0.74

manship

0.72

coded

0.70

soever

0.66

 before

0.65

 apiece

0.64

Activations Density 0.036%

phrases indicating repetition or frequency

mentions of repeated actions or occurrences

No Comments

No Known Activations