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

ogly

-0.73

omy

-0.72

affer

-0.70

 mathemat

-0.69

chart

-0.69

 peanuts

-0.69

nesday

-0.68

cher

-0.68

phi

-0.68

isable

-0.68

POSITIVE LOGITS

UST

0.66

 Alexa

0.66

sed

0.63

 Supply

0.62

ilib

0.61

amina

0.61

ses

0.59

 Yosemite

0.59

 Gorge

0.58

 incoming

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.