INDEX

Explanations

instances where permission or prohibition is discussed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "allow" and its variations

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

enegger

-0.68

 Soldier

-0.68

nard

-0.66

star

-0.65

borough

-0.64

bard

-0.64

athan

-0.63

kind

-0.62

figure

-0.62

kaya

-0.61

POSITIVE LOGITS

Reviewer

0.91

us

0.71

ipient

0.71

opol

0.71

auga

0.70

 exemptions

0.69

 rapists

0.67

 disclaim

0.66

Ĭ±

0.65

 exceptions

0.65

Activations Density 0.043%

instances where permission or prohibition is discussed

instances of the word "allow" and its variations

No Comments

No Known Activations