INDEX

Explanations

mentions of tattoos

oai_token-act-pair · gpt-3.5-turbo

words related to tattoos

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

leep

-0.74

å£«

-0.73

EH

-0.70

theless

-0.67

IDES

-0.67

audi

-0.66

ppe

-0.66

ĨĴ

-0.65

eger

-0.65

ESSION

-0.64

POSITIVE LOGITS

 tattoos

0.97

 tattoo

0.91

 Tatt

0.88

 pigment

0.87

 artist

0.86

 tatt

0.82

ink

0.81

 aesthetic

0.80

 scars

0.80

eful

0.78

Activations Density 0.038%

mentions of tattoos

words related to tattoos

No Comments

No Known Activations