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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

catentry

-0.78

 Activate

-0.71

 Learns

-0.69

atio

-0.68

SourceFile

-0.67

anium

-0.67

esm

-0.66

wcs

-0.65

rosso

-0.64

packs

-0.63

POSITIVE LOGITS

 cuff

0.69

ILE

0.64

artisan

0.63

dim

0.60

 satirical

0.60

headed

0.58

entin

0.58

orce

0.57

ilitary

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.