INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Bulg

-0.82

AOL

-0.72

AF

-0.67

ADC

-0.65

bsite

-0.63

gie

-0.62

 captcha

-0.62

chain

-0.61

RP

-0.60

 harass

-0.59

POSITIVE LOGITS

arten

0.74

PLIED

0.73

igham

0.71

interstitial

0.70

ajor

0.70

Italy

0.70

ysics

0.68

NZ

0.68

Gaza

0.67

 sidx

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.