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

interstitial

-1.02

etheless

-0.74

piracy

-0.71

VALUE

-0.70

Offline

-0.69

javascript

-0.68

notice

-0.68

conservancy

-0.67

ortium

-0.66

EStream

-0.66

POSITIVE LOGITS

icz

0.84

 Fraz

0.73

 Jacket

0.70

 Baxter

0.69

 Dimension

0.69

Geh

0.69

Cub

0.67

arium

0.66

Yug

0.66

 Dealer

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.