INDEX

Explanations

mentions of sides or perspectives, often related to politics or social issues

oai_token-act-pair · gpt-3.5-turbo

negative political affiliations or sentiments

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

ĸļ

-0.85

 layers

-0.74

 partName

-0.72

 Wonderland

-0.71

 ILCS

-0.70

 SHARES

-0.70

 ..........

-0.69

Nig

-0.69

Ago

-0.68

 beetles

-0.68

POSITIVE LOGITS

establishment

1.22

social

1.21

government

1.15

development

1.04

choice

0.99

capitalist

0.99

cycl

0.97

competitive

0.97

claimed

0.97

interest

0.96

Activations Density 0.023%

mentions of sides or perspectives, often related to politics or social issues

negative political affiliations or sentiments

No Comments

No Known Activations