INDEX

Explanations

mentions of aggressive actions or behaviors

oai_token-act-pair · gpt-3.5-turbo

instances of the word "aggressive" and its variations in context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

obyl

-0.98

ĸļ

-0.89

owship

-0.83

clips

-0.78

umbo

-0.76

udder

-0.74

atch

-0.71

 Alive

-0.70

âĢ¢âĢ¢âĢ¢âĢ¢

-0.70

ARDIS

-0.70

POSITIVE LOGITS

 aggressive

1.04

aggressive

0.84

 behavior

0.83

 tendencies

0.83

 aggression

0.81

 aggressively

0.81

 behaviour

0.79

 posture

0.78

 tactics

0.77

 stance

0.77

Activations Density 0.016%

mentions of aggressive actions or behaviors

instances of the word "aggressive" and its variations in context

No Comments

No Known Activations