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

rera

-0.75

istries

-0.69

fold

-0.68

ihara

-0.67

ieties

-0.66

unts

-0.66

anan

-0.65

loaded

-0.62

metics

-0.62

eer

-0.61

POSITIVE LOGITS

OTAL

0.68

 Cosponsors

0.63

hero

0.63

ipient

0.61

Rocket

0.61

quickShipAvailable

0.61

ularity

0.60

achusetts

0.59

cit

0.59

etime

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.