INDEX

Explanations

phrases indicating repetition or frequency

oai_token-act-pair · gpt-3.5-turbo

references to 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 @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Reviewer

-0.90

XT

-0.78

 heirs

-0.77

ourt

-0.68

rats

-0.67

Marginal

-0.66

DIT

-0.65

andr

-0.62

etermination

-0.62

rera

-0.62

POSITIVE LOGITS

 consecut

0.98

points

0.87

 throughout

0.86

 during

0.74

 apiece

0.74

 before

0.72

cale

0.71

lot

0.71

coded

0.71

orial

0.70

Activations Density 0.054%

phrases indicating repetition or frequency

references to repeated actions or occurrences

No Comments

No Known Activations