INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

bom

-0.68

minist

-0.68

erno

-0.68

gib

-0.66

 confir

-0.66

atche

-0.65

oslav

-0.63

erville

-0.62

 craw

-0.58

rang

-0.57

POSITIVE LOGITS

gyn

0.68

kefeller

0.66

ãĤī

0.65

pload

0.64

ãĥ¤

0.64

âķĲâķĲ

0.63

shi

0.61

vous

0.61

 pairing

0.60

mega

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.