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

tymology

-0.83

FactoryReloaded

-0.80

enhagen

-0.77

hid

-0.77

gypt

-0.77

thora

-0.74

ãĤ¶

-0.72

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.72

regon

-0.71

Accessory

-0.69

POSITIVE LOGITS

 Aren

0.62

 Tide

0.62

estones

0.60

 Wraith

0.60

 Butterfly

0.60

 Newsweek

0.59

't

0.59

 Seah

0.58

tox

0.58

 Norris

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.