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

Ħ¢

-0.83

wana

-0.77

ILA

-0.76

ilic

-0.74

RI

-0.74

IENT

-0.73

SHA

-0.73

urity

-0.72

WE

-0.70

ORE

-0.70

POSITIVE LOGITS

abouts

0.65

deg

0.64

gio

0.64

lights

0.63

cas

0.63

 Greenwood

0.62

 Sergeant

0.62

baum

0.61

Cas

0.61

 Fernand

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.