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

pmwiki

-0.68

Reviewer

-0.64

Osw

-0.64

enough

-0.63

 Lets

-0.63

csv

-0.63

 foil

-0.63

iers

-0.60

 Finder

-0.59

 symp

-0.58

POSITIVE LOGITS

ª

0.74

OOOOOOOO

0.67

ounty

0.66

ernandez

0.65

ÃŃa

0.65

vae

0.63

µ

0.63

OCK

0.62

ifier

0.61

ocket

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.