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

ISC

-0.68

heit

-0.67

atson

-0.67

-0.66

EW

-0.64

authorized

-0.64

 WARN

-0.63

ISH

-0.62

 feared

-0.62

POSITIVE LOGITS

rament

0.76

als

0.66

arov

0.65

Frag

0.63

imedia

0.63

edes

0.63

edit

0.62

edIn

0.62

guy

0.62

illac

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.