INDEX

Explanations

mentions of the word "wheels" or variations of the word

oai_token-act-pair · gpt-3.5-turbo

the presence of specific names or references, particularly involving "Wheaton" or variations thereof

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

 Defenders

-0.78

ographers

-0.73

pmwiki

-0.70

EMBER

-0.69

âĸ¬

-0.68

UAL

-0.65

 Gallery

-0.63

arios

-0.63

uated

-0.62

istically

-0.62

POSITIVE LOGITS

eling

0.92

Whe

0.89

esome

0.88

tted

0.88

velt

0.87

elin

0.86

ither

0.86

ldon

0.86

itness

0.85

lp

0.85

Activations Density 0.013%

mentions of the word "wheels" or variations of the word

the presence of specific names or references, particularly involving "Wheaton" or variations thereof

No Comments

No Known Activations