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

è¦ļéĨĴ

-0.76

NRS

-0.68

 Seventh

-0.66

SAS

-0.65

rin

-0.64

 urgency

-0.63

isu

-0.63

NI

-0.62

sen

-0.62

KER

-0.62

POSITIVE LOGITS

 destro

0.81

oute

0.71

itute

0.68

 undermin

0.65

bars

0.65

hower

0.65

peg

0.64

jriwal

0.64

DonaldTrump

0.63

azeera

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.