INDEX

Explanations

phrases related to violation of rules or laws

oai_token-act-pair · gpt-3.5-turbo

phrases indicating violations of laws or regulations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GROUND

-0.63

idays

-0.62

 orally

-0.61

iances

-0.57

 Illum

-0.56

Finish

-0.55

 awoken

-0.54

 succeed

-0.53

 overcame

-0.53

 intending

-0.52

POSITIVE LOGITS

escap

1.26

humane

1.23

essential

1.07

offensive

1.06

authent

1.04

 jeopardy

1.04

 contradiction

1.03

arg

1.01

ext

0.99

 fact

0.97

Activations Density 0.102%

phrases related to violation of rules or laws

phrases indicating violations of laws or regulations

No Comments

No Known Activations