INDEX

Explanations

words related to illegal actions

oai_token-act-pair · gpt-3.5-turbo

words related to illicit or illegal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sets

-0.71

STON

-0.65

itness

-0.63

skill

-0.62

agher

-0.62

SOURCE

-0.59

ĪĴ

-0.59

birds

-0.58

mir

-0.58

atson

-0.58

POSITIVE LOGITS

icit

1.57

inous

0.79

ulus

0.78

iaz

0.76

atively

0.73

iasis

0.71

ative

0.70

ums

0.70

uously

0.67

inent

0.66

Activations Density 0.008%

words related to illegal actions

words related to illicit or illegal activities

No Comments

No Known Activations