INDEX

Explanations

words related to sociology and societal topics

oai_token-act-pair · gpt-3.5-turbo

references to sociology and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Kavanaugh

-0.80

 Centauri

-0.78

ACTED

-0.69

 Gemini

-0.67

 Everest

-0.65

PRES

-0.65

 Fallen

-0.64

 McConnell

-0.62

 veiled

-0.62

MENTS

-0.62

POSITIVE LOGITS

keye

1.12

iological

0.93

iet

0.89

reth

0.88

oro

0.87

ieties

0.84

iologist

0.83

soc

0.83

oS

0.83

iper

0.81

Activations Density 0.006%

words related to sociology and societal topics

references to sociology and related terms

No Comments

No Known Activations