INDEX

Explanations

references to news sources or organizations

oai_token-act-pair · gpt-3.5-turbo

terms related to news, media outlets, and journalism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

reenshot

-0.81

oiler

-0.81

ãĤ©

-0.78

vertisements

-0.64

 filler

-0.62

 blur

-0.61

 Christensen

-0.60

arov

-0.60

................................................................

-0.59

hoe

-0.58

POSITIVE LOGITS

Chem

0.90

Site

0.86

Games

0.85

Machine

0.85

Gold

0.83

WithNo

0.82

west

0.79

ventory

0.79

swers

0.78

elaide

0.78

Activations Density 0.195%

references to news sources or organizations

terms related to news, media outlets, and journalism

No Comments

No Known Activations