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

rology

-0.64

hower

-0.62

jri

-0.61

 sectarian

-0.61

retty

-0.60

perial

-0.60

mson

-0.60

paralle

-0.59

 Jesuit

-0.58

HUM

-0.58

POSITIVE LOGITS

ellen

0.77

ilda

0.75

imar

0.74

redo

0.73

itus

0.69

anza

0.67

essor

0.65

 REUTERS

0.64

appa

0.64

gotten

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.