INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Jews

-0.71

OTS

-0.71

×Ļ×

-0.68

ãĤ§

-0.62

strings

-0.61

displayText

-0.61

\">

-0.61

Ð´

-0.61

Ô

-0.59

}"

-0.59

POSITIVE LOGITS

asus

0.74

uno

0.72

lyak

0.70

icipated

0.66

 nodd

0.64

emort

0.64

owan

0.60

 plateau

0.59

ensis

0.59

wered

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.