INDEX

Explanations

mentions of smoking-related terms

oai_token-act-pair · gpt-3.5-turbo

references to smoking and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

assian

-0.81

tell

-0.70

 Defenders

-0.69

translation

-0.69

 Vector

-0.67

telling

-0.66

Philipp

-0.65

Nou

-0.65

ousse

-0.65

HCR

-0.64

POSITIVE LOGITS

 cessation

1.31

 smoking

1.19

 smoked

1.08

 smoker

1.08

 cigarettes

1.07

 smoke

1.03

 cigars

1.02

 habits

0.96

 tobacco

0.95

 smokers

0.93

Activations Density 0.015%

mentions of smoking-related terms

references to smoking and its effects

No Comments

No Known Activations