INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arget

-0.79

pmwiki

-0.72

CoC

-0.71

aste

-0.66

acks

-0.64

terday

-0.64

 contem

-0.62

Sov

-0.62

hov

-0.60

ack

-0.59

POSITIVE LOGITS

brother

0.76

forth

0.67

ì

0.64

Lon

0.62

shall

0.62

èĢ

0.61

 Provided

0.60

wit

0.59

ilon

0.59

keepers

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.