INDEX

Explanations

instances where people are discussing, explaining, or pointing out specific topics or issues

oai_token-act-pair · gpt-3.5-turbo

expressions of dissatisfaction or complaints about various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

yss

-0.76

engers

-0.73

earchers

-0.73

externalActionCode

-0.72

 Survivors

-0.69

ngth

-0.65

elaide

-0.61

wana

-0.61

 pione

-0.61

displayText

-0.61

POSITIVE LOGITS

 crap

1.14

 shit

1.10

 shitty

1.09

 crappy

1.01

 stupid

1.01

 goddamn

0.99

 bullshit

0.95

 pointless

0.94

 fucking

0.93

 fuck

0.91

Activations Density 0.769%

instances where people are discussing, explaining, or pointing out specific topics or issues

expressions of dissatisfaction or complaints about various topics

No Comments

No Known Activations