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

Constructed

-0.92

VID

-0.66

[*]

-0.65

NAT

-0.64

 Puzzles

-0.61

 Pione

-0.58

 repe

-0.58

 autom

-0.58

 Closed

-0.57

 âĶľ

-0.57

POSITIVE LOGITS

ython

0.81

berra

0.80

etheless

0.79

ither

0.75

assic

0.74

ookie

0.74

apons

0.73

henko

0.73

ithub

0.73

akin

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.