INDEX

Explanations

gender-related terms and phrases

oai_token-act-pair · gpt-3.5-turbo

discussions surrounding gender identity and corresponding facilities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Uncharted

-0.68

IRC

-0.67

Hur

-0.65

rawdownloadcloneembedreportprint

-0.65

emonium

-0.65

 thunder

-0.65

 Luffy

-0.65

 Greenpeace

-0.63

 Damn

-0.63

isSpecialOrderable

-0.63

POSITIVE LOGITS

 lawfully

0.82

 unlawfully

0.69

disabled

0.68

 expires

0.68

 caregivers

0.61

 disabled

0.60

 safely

0.59

gins

0.58

rique

0.58

 thinner

0.57

Activations Density 0.806%

gender-related terms and phrases

discussions surrounding gender identity and corresponding facilities

No Comments

No Known Activations