INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ļéĨĴ

-0.70

ãĤ´ãĥ³

-0.70

kamp

-0.68

 Leilan

-0.68

 Canaan

-0.65

 lamb

-0.65

 medi

-0.64

adr

-0.63

issance

-0.63

ogyn

-0.62

POSITIVE LOGITS

hetical

0.65

0.63

hesis

0.63

ipolar

0.60

yeah

0.60

aspx

0.60

 HSBC

0.59

zn

0.59

hands

0.58

profits

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.