INDEX

Explanations

phrases or sentences indicating permission or enabling of actions

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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

borough

-0.80

xon

-0.72

bard

-0.69

bon

-0.68

enegger

-0.68

need

-0.67

kaya

-0.66

nard

-0.63

leaf

-0.62

bons

-0.61

POSITIVE LOGITS

us

0.83

Reviewer

0.82

me

0.73

ipient

0.69

 passers

0.67

 them

0.67

him

0.67

 rapists

0.66

ANCE

0.66

ances

0.66

Activations Density 0.063%

phrases or sentences indicating permission or enabling of actions

instances of the word "allow" and its variations

No Comments

No Known Activations