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

advertising

-0.79

SourceFile

-0.75

IRE

-0.73

BILL

-0.73

anova

-0.71

RIC

-0.68

gered

-0.67

Īè

-0.67

Cu

-0.67

PLA

-0.67

POSITIVE LOGITS

 Nanto

0.69

 Cutter

0.66

abouts

0.65

 Immigration

0.64

 Destination

0.63

usalem

0.63

cru

0.63

ape

0.62

asin

0.61

 donor

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.