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

HRC

-0.75

\\\\\\\\

-0.71

 condu

-0.62

chnology

-0.61

','

-0.61

 strat

-0.60

 Wasserman

-0.60

 unic

-0.59

arnaev

-0.59

 helic

-0.58

POSITIVE LOGITS

bum

0.83

sound

0.80

Sound

0.74

keeper

0.72

gers

0.71

Spot

0.70

cum

0.69

Plus

0.68

meaning

0.67

band

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.