INDEX

Explanations

proper nouns or names of people and entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names

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

behind

-0.78

kered

-0.72

adem

-0.71

drawn

-0.69

idth

-0.69

ECTION

-0.68

ymm

-0.66

abre

-0.66

hift

-0.62

NetMessage

-0.60

POSITIVE LOGITS

Pure

0.63

JA

0.61

âĢ²

0.61

 Advis

0.60

 himself

0.60

zik

0.59

erion

0.58

 Advisor

0.57

 believing

0.57

 Young

0.56

Activations Density 0.735%

proper nouns or names of people and entities

proper nouns or names

No Comments

No Known Activations