INDEX

Explanations

names or terms with the prefix "As"

oai_token-act-pair · gpt-3.5-turbo

proper nouns or names

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

Leaks

-0.67

{"

-0.63

 Porsche

-0.61

Zot

-0.57

 snap

-0.57

 mean

-0.56

Koz

-0.56

uncture

-0.53

 Rats

-0.53

 Venezuel

-0.53

POSITIVE LOGITS

ylum

1.03

wered

0.96

agus

0.86

itably

0.79

sembly

0.77

ociated

0.77

acus

0.77

cery

0.76

ibo

0.74

allah

0.73

Activations Density 0.066%

names or terms with the prefix "As"

proper nouns or names

No Comments

No Known Activations