INDEX

Explanations

words related to social or political issues and actions, especially those with negative connotations

oai_token-act-pair · gpt-3.5-turbo

terms associated with anti-arguments or opposition to various issues

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

Rue

-0.70

 dots

-0.66

 Mock

-0.65

KNOWN

-0.65

staking

-0.62

 STATS

-0.62

McH

-0.61

 notebooks

-0.60

mit

-0.59

Nun

-0.59

POSITIVE LOGITS

usterity

0.99

roleum

0.86

otic

0.86

otics

0.84

byter

0.80

aphael

0.79

ilib

0.78

osher

0.78

amacare

0.76

ucl

0.76

Activations Density 0.132%

words related to social or political issues and actions, especially those with negative connotations

terms associated with anti-arguments or opposition to various issues

No Comments

No Known Activations