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

 Voting

-0.61

 jails

-0.61

 apartheid

-0.61

 Assessment

-0.61

 theorem

-0.61

 Abrams

-0.60

Java

-0.58

 footballer

-0.58

 Apart

-0.57

abad

-0.57

POSITIVE LOGITS

amen

0.77

pez

0.71

ads

0.70

aintain

0.70

 save

0.67

Pwr

0.67

ilings

0.67

idon

0.66

inosaur

0.66

ione

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.