INDEX

Explanations

references to news articles or publications

oai_token-act-pair · gpt-3.5-turbo

segments of text labeled as "Article."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nesota

-0.85

awar

-0.83

aukee

-0.83

adows

-0.81

ergic

-0.79

cffffcc

-0.78

boa

-0.77

etsk

-0.77

cffff

-0.76

eco

-0.76

POSITIVE LOGITS

ICLE

0.82

 Continued

0.81

meal

0.77

 Articles

0.73

ual

0.70

 Mobil

0.68

XVI

0.68

witz

0.68

 subscribed

0.63

 Consent

0.63

Activations Density 0.015%

references to news articles or publications

segments of text labeled as "Article."

No Comments

No Known Activations