INDEX

Explanations

references to a specific political party

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

obyl

-0.80

pel

-0.74

 Yellowstone

-0.73

 Twain

-0.70

 Jehovah

-0.68

 Dickens

-0.67

 Hurricanes

-0.67

 Manson

-0.67

 Velocity

-0.66

htaking

-0.66

POSITIVE LOGITS

 affili

0.79

 Party

0.78

 leadership

0.78

 affiliation

0.78

 membership

0.77

Leader

0.76

 parliamentary

0.75

 senate

0.73

 electoral

0.71

MLA

0.71

Activations Density 0.021%

references to a specific political party

No Comments

No Known Activations