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

INGTON

-0.79

 Confederation

-0.71

interstitial

-0.68

stood

-0.68

stead

-0.68

 corrid

-0.67

kson

-0.66

yt

-0.66

circle

-0.63

Vill

-0.63

POSITIVE LOGITS

 Clojure

0.68

lime

0.67

RB

0.66

ancial

0.63

etting

0.61

ire

0.60

FY

0.59

eties

0.59

aby

0.58

et

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.