INDEX

Explanations

actions that involve physical force or aggression

oai_token-act-pair · gpt-3.5-turbo

actions and scenarios involving physical interactions or conflict

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Polit

-0.69

 Libertarian

-0.66

Policy

-0.65

 Strategy

-0.63

NBN

-0.63

ourcing

-0.63

 Netanyahu

-0.63

 Statement

-0.62

 Investigative

-0.62

 Liberal

-0.62

POSITIVE LOGITS

 undet

0.80

 nearby

0.79

 eternity

0.79

 unsuspecting

0.79

 prest

0.76

 throb

0.73

 menstru

0.73

 vulner

0.72

 blades

0.71

 ankles

0.70

Activations Density 2.122%

actions that involve physical force or aggression

actions and scenarios involving physical interactions or conflict

No Comments

No Known Activations