INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ilion

-0.76

veyard

-0.73

kefeller

-0.73

psy

-0.72

ppel

-0.71

ieties

-0.70

onut

-0.69

bably

-0.67

hler

-0.67

velt

-0.66

POSITIVE LOGITS

Sword

0.69

 tert

0.63

 QuÃ©

0.62

lights

0.61

SA

0.61

RAW

0.59

CBC

0.59

RW

0.58

RL

0.58

KN

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.