INDEX

Explanations

medical terms or medications prefixed with "cis"

oai_token-act-pair · gpt-3.5-turbo

terms related to gender identity and media representation

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

 confir

-0.73

culosis

-0.72

srf

-0.71

ternity

-0.68

ysis

-0.67

XIV

-0.66

avorite

-0.65

idan

-0.65

zbek

-0.64

POSITIVE LOGITS

otte

0.97

agos

0.90

sel

0.83

erva

0.83

tern

0.82

oeuv

0.81

amar

0.80

vest

0.79

riage

0.76

jury

0.75

Activations Density 0.066%

medical terms or medications prefixed with "cis"

terms related to gender identity and media representation

No Comments

No Known Activations