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

 Satisf

-0.64

 Facts

-0.62

 Ples

-0.60

Material

-0.60

URRENT

-0.60

byter

-0.59

 Wass

-0.59

 Flower

-0.59

ueless

-0.59

Keeping

-0.58

POSITIVE LOGITS

iggle

0.86

chwitz

0.79

sembly

0.74

abad

0.72

wine

0.70

oute

0.66

anne

0.66

ude

0.66

reau

0.65

aukee

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.