INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

hess

-0.77

pron

-0.73

river

-0.68

enegger

-0.68

jri

-0.65

 Seym

-0.64

minecraft

-0.64

ihad

-0.63

 impro

-0.62

berra

-0.61

POSITIVE LOGITS

DK

0.77

imity

0.70

isode

0.65

achment

0.63

Ð´

0.61

uscript

0.60

 returned

0.60

 encounters

0.59

();

0.58

 disbanded

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.