INDEX

Explanations

names or proper nouns

oai_token-act-pair · gpt-3.5-turbo

prominent names or proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-1.02

ãĤ¼ãĤ¦ãĤ¹

-0.81

CLASSIFIED

-0.69

 Archae

-0.65

 EDITION

-0.63

 âĢº

-0.63

 Madame

-0.63

ãĥŁ

-0.62

ãģ®å

-0.60

Mt

-0.60

POSITIVE LOGITS

leck

0.95

auld

0.89

ynes

0.86

oval

0.83

reat

0.82

idy

0.82

ridge

0.82

ees

0.80

ley

0.79

reath

0.79

Activations Density 0.191%

names or proper nouns

prominent names or proper nouns

No Comments

No Known Activations