INDEX

Explanations

mentions of the word "domestic"

oai_token-act-pair · gpt-3.5-turbo

references to domestic issues or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

uden

-0.89

uyomi

-0.84

umper

-0.81

ombs

-0.79

*/(

-0.79

osen

-0.77

edin

-0.74

kson

-0.71

atto

-0.70

 GOODMAN

-0.70

POSITIVE LOGITS

 Violence

1.00

 affairs

0.93

 violence

0.86

 Domestic

0.79

violence

0.78

 appliances

0.76

 domestic

0.76

 tranqu

0.75

 combustion

0.74

law

0.73

Activations Density 0.011%

mentions of the word "domestic"

references to domestic issues or topics

No Comments

No Known Activations