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

ittle

-0.83

oaded

-0.76

OY

-0.74

everal

-0.74

itters

-0.71

INESS

-0.68

DIV

-0.68

inance

-0.67

hovah

-0.67

 tremend

-0.65

POSITIVE LOGITS

apt

0.75

ras

0.67

library

0.64

 altar

0.64

aut

0.63

aton

0.62

kh

0.61

ath

0.61

 library

0.61

 Wond

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.