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

bos

-0.78

hner

-0.70

utra

-0.68

 Refugees

-0.65

ibe

-0.65

central

-0.63

èĢħ

-0.61

eker

-0.60

 Refugee

-0.60

 Dynamics

-0.59

POSITIVE LOGITS

asonic

0.78

awa

0.76

rative

0.70

 ILCS

0.70

å§«

0.70

OW

0.67

 sidx

0.66

poons

0.65

Viz

0.64

 dilig

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.