INDEX

Explanations

Unrelated and random text snippets

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term 'Un' followed by a number indicating censorship or uncredited sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

OPLE

-0.96

 briefs

-0.74

 cone

-0.71

 tomat

-0.69

anwhile

-0.69

ä»£

-0.65

azine

-0.65

Peb

-0.65

=-=-=-=-=-=-=-=-

-0.64

 slopes

-0.64

POSITIVE LOGITS

idad

0.99

cles

0.97

ortunately

0.94

affiliated

0.90

classified

0.87

ities

0.86

stable

0.86

usual

0.85

Un

0.85

ruly

0.84

Activations Density 0.006%

Unrelated and random text snippets

occurrences of the term 'Un' followed by a number indicating censorship or uncredited sources

No Comments

No Known Activations