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

 Hispan

-0.67

seek

-0.63

gement

-0.63

 evolve

-0.60

XD

-0.59

 captcha

-0.58

 inputs

-0.58

 Regions

-0.57

Tang

-0.57

../

-0.57

POSITIVE LOGITS

ANY

0.71

asonable

0.71

anes

0.67

ione

0.66

STA

0.66

CLA

0.65

VG

0.65

Sto

0.65

WI

0.64

uania

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.