INDEX

Explanations

terms related to significant actions or decisions being made

oai_token-act-pair · gpt-3.5-turbo

references to significant actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

omial

-0.73

 sqor

-0.70

etheless

-0.67

aez

-0.67

vae

-0.66

english

-0.64

sung

-0.63

aylor

-0.63

oola

-0.63

 Koran

-0.62

POSITIVE LOGITS

 toward

0.94

 towards

0.93

able

0.85

ments

0.84

backs

0.82

over

0.76

igraph

0.73

rers

0.71

abouts

0.71

 decisively

0.71

Activations Density 0.032%

terms related to significant actions or decisions being made

references to significant actions or decisions

No Comments

No Known Activations