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

edia

-0.72

alian

-0.70

nation

-0.67

aceous

-0.64

iegel

-0.63

atial

-0.63

lamm

-0.61

endant

-0.61

opot

-0.61

yrus

-0.60

POSITIVE LOGITS

ãĥ¼ãĥĨ

0.71

Versions

0.63

 shorth

0.61

llo

0.60

 Compton

0.60

OTAL

0.59

Keefe

0.58

ipation

0.57

 misdem

0.57

ro

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.