INDEX

Explanations

titles or headings within text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "title" along with its variations and associated numbers

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

gm

-0.79

ombo

-0.68

 spice

-0.66

olson

-0.66

 Leone

-0.64

anthrop

-0.62

verages

-0.62

 Spice

-0.62

 Spicer

-0.61

ASE

-0.60

POSITIVE LOGITS

manship

0.98

marks

0.89

title

0.86

¥µ

0.84

pad

0.80

mark

0.79

holder

0.79

marked

0.79

åĭ

0.77

card

0.76

Activations Density 0.026%

titles or headings within text

instances of the word "title" along with its variations and associated numbers

No Comments

No Known Activations