INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

achy

-0.75

esson

-0.75

acs

-0.73

nell

-0.72

vacc

-0.72

cham

-0.71

Graphics

-0.71

burgh

-0.71

 Glacier

-0.70

 Glac

-0.69

POSITIVE LOGITS

lif

0.84

 Kuro

0.68

 reven

0.67

pot

0.66

 Logged

0.64

idon

0.64

Yok

0.63

 stimulus

0.62

Yin

0.62

oaded

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.