INDEX

Explanations

adjectives and nouns related to unfairness

oai_token-act-pair · gpt-3.5-turbo

references to unfairness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hent

-0.89

apse

-0.76

audi

-0.73

ien

-0.71

udder

-0.70

gdala

-0.70

ational

-0.70

lang

-0.69

ince

-0.69

arians

-0.68

POSITIVE LOGITS

nesses

1.00

 Advantage

0.94

 advantage

0.93

 unfair

0.87

 dismissal

0.86

 burden

0.83

 disadvantage

0.81

 compensation

0.81

 advantages

0.80

 burdens

0.80

Activations Density 0.043%

adjectives and nouns related to unfairness

references to unfairness in various contexts

No Comments

No Known Activations