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

dies

-0.75

ipeg

-0.72

abouts

-0.70

eni

-0.68

cond

-0.68

agon

-0.67

ulence

-0.65

yip

-0.64

rational

-0.63

olition

-0.63

POSITIVE LOGITS

 Nich

0.81

Zan

0.75

âĺĨ

0.67

AFTA

0.66

Kar

0.66

 Kirin

0.65

Kas

0.65

 Medals

0.65

ITT

0.63

Kar

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.