INDEX

Explanations

events or situations involving defiance or resistance

oai_token-act-pair · gpt-3.5-turbo

instances of defiance or disobedience against authority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iar

-1.01

oan

-0.83

ivities

-0.78

thora

-0.76

ilitating

-0.74

NetMessage

-0.74

ochond

-0.73

rim

-0.73

anwhile

-0.73

affer

-0.73

POSITIVE LOGITS

edient

0.91

 obedience

0.81

obe

0.79

 disobedience

0.79

FUL

0.76

 defy

0.76

 conformity

0.75

fulness

0.75

GBT

0.73

 disob

0.67

Activations Density 0.048%

events or situations involving defiance or resistance

instances of defiance or disobedience against authority

No Comments

No Known Activations