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

-0.91

©¶æ¥µ

-0.91

©¶æ

-0.84

achev

-0.77

acqu

-0.76

PokÃ©mon

-0.75

catentry

-0.74

¥µ

-0.72

ĻĤ

-0.71

ħĭ

-0.66

POSITIVE LOGITS

Vol

0.65

istan

0.63

yz

0.62

 Sched

0.57

atsu

0.57

 bast

0.57

ublic

0.57

ok

0.57

lust

0.57

ya

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.