INDEX

Explanations

mentions of drug-related actions and terms

oai_token-act-pair · gpt-3.5-turbo

keywords related to health and safety issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ostic

-0.61

ariat

-0.61

 Panc

-0.57

manship

-0.57

 Azerb

-0.56

naires

-0.56

orate

-0.55

 Pist

-0.55

cape

-0.53

eous

-0.53

POSITIVE LOGITS

thumbnails

0.55

 brutality

0.51

 seizures

0.51

both

0.50

HDR

0.50

anooga

0.50

Values

0.49

%]

0.48

bleacher

0.48

URL

0.47

Activations Density 0.183%

mentions of drug-related actions and terms

keywords related to health and safety issues

No Comments

No Known Activations