INDEX

Explanations

proper nouns related to various entities like companies, individuals, and organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ebin

-0.60

asty

-0.59

ezvous

-0.58

rontal

-0.58

owship

-0.57

bys

-0.57

nova

-0.55

kick

-0.54

isoft

-0.54

inces

-0.52

POSITIVE LOGITS

 sake

1.09

it

0.83

 purposes

0.82

 reasons

0.76

 there

0.76

erning

0.75

 alone

0.70

 wanting

0.66

 alike

0.66

 this

0.62

Activations Density 0.187%

proper nouns related to various entities like companies, individuals, and organizations

proper nouns and specific entities

No Comments

No Known Activations