INDEX

Explanations

mentions of small or young individuals, specifically when used as term of endearment or to indicate size

oai_token-act-pair · gpt-3.5-turbo

the word "little" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

chwitz

-0.90

anwhile

-0.82

igham

-0.78

 conclud

-0.77

idential

-0.75

arbon

-0.74

cius

-0.73

orthy

-0.73

idents

-0.72

ï¸

-0.71

POSITIVE LOGITS

bit

0.98

 girl

0.87

kid

0.85

 girls

0.83

boy

0.82

 boys

0.79

 helper

0.76

 snippets

0.75

 brother

0.75

 sister

0.75

Activations Density 0.026%

mentions of small or young individuals, specifically when used as term of endearment or to indicate size

the word "little" in various contexts

No Comments

No Known Activations