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

ESCO

-0.76

 interfering

-0.66

 Chand

-0.66

 Carlo

-0.62

 prepar

-0.60

soDeliveryDate

-0.60

 endot

-0.59

aukee

-0.59

isma

-0.59

 Sicily

-0.58

POSITIVE LOGITS

ridge

0.92

BF

0.76

riad

0.71

:{

0.70

claimer

0.68

:]

0.66

ä¹ĭ

0.65

Ô

0.65

=]

0.63

 Blaze

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.