INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sth

-0.73

xus

-0.73

 largeDownload

-0.70

heses

-0.68

holders

-0.67

 ratios

-0.66

holder

-0.65

ery

-0.64

writers

-0.63

 Authors

-0.63

POSITIVE LOGITS

ĵ

0.69

RAY

0.68

ãĤ´

0.66

fitting

0.65

ricted

0.63

Tue

0.63

Made

0.63

ãĥĺ

0.62

 Release

0.62

IED

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.