INDEX

Explanations

references to physical objects related to writing or organizing thoughts, such as notebooks and pens

oai_token-act-pair · gpt-3.5-turbo

mentions of notebooks and related terms

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

rer

-0.90

rie

-0.88

tale

-0.86

bots

-0.86

inations

-0.84

rum

-0.83

idi

-0.82

riages

-0.82

amount

-0.82

bed

-0.80

POSITIVE LOGITS

externalActionCode

0.87

EDT

0.80

tee

0.78

CRIP

0.73

manship

0.70

HK

0.68

WS

0.67

 Ryder

0.66

tnc

0.66

 drinking

0.62

Activations Density 0.026%

references to physical objects related to writing or organizing thoughts, such as notebooks and pens

mentions of notebooks and related terms

No Comments

No Known Activations