INDEX

Explanations

keywords related to politics

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "politics" and related variations

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

imates

-0.87

uran

-0.74

actory

-0.72

clud

-0.68

amination

-0.68

untary

-0.65

 Vera

-0.65

ependence

-0.64

Universal

-0.63

oa

-0.62

POSITIVE LOGITS

 correctness

1.08

clinton

0.85

eering

0.85

atism

0.83

hare

0.82

cape

0.79

chool

0.78

manship

0.77

esp

0.73

hip

0.73

Activations Density 0.036%

keywords related to politics

mentions of the word "politics" and related variations

No Comments

No Known Activations