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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zac

-0.87

inches

-0.75

ZI

-0.73

itton

-0.66

haul

-0.66

skirts

-0.66

 Wrap

-0.65

Ago

-0.65

 IMAGES

-0.64

anz

-0.64

POSITIVE LOGITS

ItemTracker

0.71

 repayment

0.68

 prem

0.67

ributed

0.67

 anonymity

0.65

Tokens

0.65

interstitial

0.63

govern

0.63

 Provincial

0.63

ourced

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.