INDEX

Explanations

mentions of employment-related terms

oai_token-act-pair · gpt-3.5-turbo

references to employment and 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

ifiers

-0.75

sonian

-0.74

gran

-0.69

ifier

-0.66

het

-0.64

olid

-0.62

las

-0.62

rx

-0.61

gery

-0.60

inx

-0.60

POSITIVE LOGITS

ment

0.85

 unions

0.84

 opportunities

0.77

Aff

0.75

rious

0.75

 ethic

0.70

 Practices

0.68

ettlement

0.67

 employment

0.67

 secretaries

0.66

Activations Density 0.018%

mentions of employment-related terms

references to employment and related issues

No Comments

No Known Activations