INDEX

Explanations

words and phrases related to discussing opinions and characteristics of groups of people

oai_token-act-pair · gpt-3.5-turbo

references to societal perceptions and stereotypes about various groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 looph

-0.69

ework

-0.65

Stretch

-0.64

Torrent

-0.63

 maneu

-0.63

vere

-0.63

 withdrew

-0.63

 defied

-0.60

 Banner

-0.60

annis

-0.60

POSITIVE LOGITS

 invariably

1.39

 usually

1.04

 inevitably

0.99

 cringe

0.98

often

0.93

usually

0.91

 referring

0.90

 typically

0.87

 reply

0.86

rase

0.83

Activations Density 0.350%

words and phrases related to discussing opinions and characteristics of groups of people

references to societal perceptions and stereotypes about various groups

No Comments

No Known Activations