INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ified

-0.98

rified

-0.95

lot

-0.83

riter

-0.81

ifies

-0.81

egg

-0.80

urgy

-0.79

imil

-0.79

binding

-0.78

blade

-0.77

POSITIVE LOGITS

UAL

0.87

elson

0.73

 Centauri

0.72

querade

0.71

uality

0.71

 Gupta

0.69

BILITY

0.69

OPLE

0.68

Ã±

0.67

agement

0.67

Activations Density 0.205%

proper nouns

proper nouns, particularly names and places

No Comments

No Known Activations