INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

osure

-0.81

 peripher

-0.79

icut

-0.72

kin

-0.68

 stabilized

-0.68

 entrants

-0.66

 horizont

-0.65

accompan

-0.63

pressed

-0.62

lig

-0.62

POSITIVE LOGITS

BN

0.73

ibus

0.69

BS

0.67

ucc

0.66

 Bans

0.64

rid

0.64

 Mill

0.62

NV

0.61

cas

0.61

bern

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.