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

Newsletter

-0.69

ared

-0.64

Me

-0.64

plane

-0.63

pmwiki

-0.61

 Monitor

-0.61

illary

-0.61

lier

-0.59

 Mount

-0.59

oran

-0.58

POSITIVE LOGITS

uesday

0.83

 defin

0.77

ãĥ´ãĤ¡

0.75

 elig

0.74

 captcha

0.71

 definitely

0.71

heit

0.70

 probably

0.69

 owed

0.69

ribut

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.