INDEX

Explanations

statements related to political figures, policies, and events

oai_token-act-pair · gpt-3.5-turbo

keywords related to political announcements or statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 roam

-0.63

 slic

-0.60

 roaming

-0.58

 cockpit

-0.55

 spawns

-0.54

uces

-0.53

 mats

-0.53

paces

-0.52

 spawn

-0.52

zona

-0.52

POSITIVE LOGITS

 Holmes

0.59

 Dunham

0.58

 Weeks

0.58

 Oprah

0.58

 Disclosure

0.57

 Rodham

0.56

 Limbaugh

0.56

Reader

0.56

 Garrison

0.56

 Nixon

0.55

Activations Density 1.723%

statements related to political figures, policies, and events

keywords related to political announcements or statements

No Comments

No Known Activations