INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

augh

-0.69

bound

-0.67

brow

-0.65

ithmetic

-0.64

rollers

-0.58

dayName

-0.58

catentry

-0.58

SUN

-0.57

 retiring

-0.57

displayText

-0.57

POSITIVE LOGITS

interstitial

0.86

ª

0.72

 Foundation

0.70

rome

0.68

pheus

0.67

rys

0.65

éŃĶ

0.65

ully

0.64

Pont

0.62

Project

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.