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

 endif

-0.68

amy

-0.65

XX

-0.64

ĩ

-0.62

æŃ

-0.59

 Lomb

-0.59

å¤©

-0.58

lag

-0.57

åİ

-0.56

ä½

-0.56

POSITIVE LOGITS

assetsadobe

0.81

apeshifter

0.79

olor

0.77

apesh

0.70

aughs

0.68

pee

0.68

racuse

0.66

rush

0.66

 enthus

0.65

 sponge

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.