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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

$$

-0.75

ovember

-0.73

awk

-0.71

rake

-0.66

duction

-0.65

atted

-0.64

"},

-0.64

RH

-0.63

yz

-0.62

SN

-0.60

POSITIVE LOGITS

 sidx

0.82

 Duty

0.76

 Volks

0.70

 Tycoon

0.66

 spons

0.66

 looph

0.65

MRI

0.65

arnaev

0.65

zbollah

0.64

uin

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.