INDEX

Explanations

mentions of new policies, regulations, or changes

oai_token-act-pair · gpt-3.5-turbo

references to new policies or regulations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Zip

-0.77

acebook

-0.76

lua

-0.74

ashtra

-0.73

ONSORED

-0.71

OGR

-0.70

umenthal

-0.70

ecause

-0.70

icio

-0.69

cius

-0.69

POSITIVE LOGITS

bies

1.33

bie

1.30

 arrivals

1.22

 additions

1.02

 edition

0.99

 millennium

0.97

 generation

0.96

 entrants

0.92

 hires

0.92

 developments

0.88

Activations Density 0.079%

mentions of new policies, regulations, or changes

references to new policies or regulations

No Comments

No Known Activations