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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amina

-0.76

arie

-0.75

uana

-0.74

uffy

-0.70

vine

-0.69

 Baal

-0.68

asma

-0.68

 Shant

-0.66

ataka

-0.63

 reel

-0.62

POSITIVE LOGITS

GMT

0.74

 integration

0.73

 fragmentation

0.70

iqueness

0.70

otin

0.70

inav

0.64

IG

0.63

 Integration

0.63

ohl

0.63

nov

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.