INDEX

Explanations

names of organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

orate

-0.79

izons

-0.71

arding

-0.70

urate

-0.69

arded

-0.68

iard

-0.67

acting

-0.65

oard

-0.63

raising

-0.62

uminati

-0.62

POSITIVE LOGITS

plings

0.82

atchewan

0.77

eways

0.77

ustain

0.76

ority

0.73

utra

0.73

earcher

0.73

arin

0.73

 Rough

0.72

ETH

0.71

Activations Density 0.169%

names of organizations

proper nouns, particularly names and organizations

No Comments

No Known Activations