INDEX

Explanations

references to historical figure Ronald Reagan

oai_token-act-pair · gpt-3.5-turbo

mentions of Ronald Reagan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ĨĴ

-0.89

tered

-0.71

âĸ¬âĸ¬

-0.66

 Flavoring

-0.65

ļ

-0.64

âĸ¬

-0.64

uns

-0.63

unal

-0.62

olulu

-0.61

 à¨

-0.61

POSITIVE LOGITS

 Reagan

1.23

omics

0.92

quist

0.79

kefeller

0.75

udeau

0.74

isma

0.71

 Eisenhower

0.71

ettes

0.71

 Jinping

0.71

baum

0.70

Activations Density 0.004%

references to historical figure Ronald Reagan

mentions of Ronald Reagan

No Comments

No Known Activations