INDEX

Explanations

news articles or headlines

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "News" in various contexts

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

ught

-0.77

 slee

-0.73

vernment

-0.71

phrine

-0.69

 goddamn

-0.69

inished

-0.68

otent

-0.68

BuyableInstoreAndOnline

-0.68

ugh

-0.67

 erect

-0.66

POSITIVE LOGITS

News

1.03

letters

1.00

NEWS

0.98

 Coverage

0.90

Reporting

0.89

 Tycoon

0.86

orial

0.86

 News

0.85

 Articles

0.83

reader

0.83

Activations Density 0.037%

news articles or headlines

occurrences of the word "News" in various contexts

No Comments

No Known Activations