INDEX

Explanations

phrases related to policy and government actions

oai_token-act-pair · gpt-3.5-turbo

references to health, education, and infrastructure-related issues

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

rend

-0.75

icol

-0.74

worldly

-0.74

ukong

-0.73

ital

-0.72

canon

-0.71

wic

-0.71

isen

-0.70

Legend

-0.70

arro

-0.70

POSITIVE LOGITS

 thereby

1.01

 consequ

0.89

 entitle

0.89

 pensions

0.82

 hence

0.82

 consequently

0.82

 thus

0.78

 welfare

0.76

etc

0.76

 secondly

0.75

Activations Density 0.479%

phrases related to policy and government actions

references to health, education, and infrastructure-related issues

No Comments

No Known Activations