INDEX

Explanations

proper nouns with 'cc' in them

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "cc" in the text

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

 Lans

-0.76

¥µ

-0.73

chest

-0.70

cknow

-0.70

velt

-0.68

staking

-0.68

esthetic

-0.68

ãĤ¤

-0.67

strument

-0.66

selves

-0.65

POSITIVE LOGITS

entric

1.18

aneers

1.13

arthy

0.98

anyon

0.95

ombat

0.94

artney

0.94

inelli

0.93

lesi

0.90

inct

0.88

annon

0.88

Activations Density 0.014%

proper nouns with 'cc' in them

occurrences of the abbreviation "cc" in the text

No Comments

No Known Activations