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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Poster

-0.75

atum

-0.71

 Destination

-0.70

 Motion

-0.68

 Lime

-0.66

Zig

-0.66

wx

-0.65

Msg

-0.65

cence

-0.65

 Rect

-0.64

POSITIVE LOGITS

»Ĵ

0.72

soDeliveryDate

0.69

oka

0.66

ãĤī

0.65

é»Ĵ

0.65

aminer

0.64

ãģª

0.64

ICLE

0.63

ãģ¦

0.62

ritch

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.