INDEX

Explanations

words related to news articles, updates, and information

oai_token-act-pair · gpt-3.5-turbo

engagement prompts and advertising content

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 respectively

-0.53

 mechanically

-0.51

 fundamentals

-0.48

 alone

-0.48

 fame

-0.47

 Valve

-0.47

 partying

-0.46

 aesthetic

-0.46

 indifferent

-0.45

 deciding

-0.45

POSITIVE LOGITS

 UNCLASSIFIED

0.83

 WATCHED

0.75

CNN

0.74

 POLIT

0.73

News

0.72

Politics

0.71

 POLITICO

0.70

embed

0.68

 Transcript

0.67

politics

0.65

Activations Density 0.874%

words related to news articles, updates, and information

engagement prompts and advertising content

No Comments

No Known Activations