INDEX

Explanations

phrases related to legal matters or official statements

oai_token-act-pair · gpt-3.5-turbo

phrases related to statements and allegations in a political context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 occasionally

-0.72

 depending

-0.71

Interstitial

-0.70

 specialize

-0.69

 somet

-0.69

pmwiki

-0.68

 whenever

-0.67

ulton

-0.67

 periodically

-0.67

 situations

-0.66

POSITIVE LOGITS

 Lavrov

0.89

 Flynn

0.81

 Tillerson

0.79

 Cohn

0.78

 Sessions

0.78

Ms

0.78

MH

0.76

 Harvey

0.76

 Pruitt

0.75

 Garland

0.75

Activations Density 0.428%

phrases related to legal matters or official statements

phrases related to statements and allegations in a political context

No Comments

No Known Activations