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

alion

-0.91

agram

-0.78

rament

-0.78

ctors

-0.74

leground

-0.72

illary

-0.71

cephal

-0.70

onet

-0.70

ifice

-0.68

 subscript

-0.68

POSITIVE LOGITS

CHAT

0.75

lander

0.63

sbm

0.62

ported

0.61

Hog

0.61

Īè

0.61

HO

0.61

spr

0.60

å½

0.60

GU

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.