INDEX

Explanations

mentions of mothers

oai_token-act-pair · gpt-3.5-turbo

references to the word "mom."

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

 Flavoring

-0.87

lihood

-0.83

REDACTED

-0.70

vernment

-0.69

ENGTH

-0.62

 Morales

-0.61

 Voting

-0.61

etting

-0.60

 Crimes

-0.59

CONT

-0.59

POSITIVE LOGITS

my

1.25

hesis

1.10

mers

1.04

ma

1.04

mer

0.92

mas

0.88

mom

0.85

wife

0.84

entary

0.84

heses

0.84

Activations Density 0.014%

mentions of mothers

references to the word "mom."

No Comments

No Known Activations