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

 Peters

-0.67

ãĥīãĥ©

-0.67

Sen

-0.65

elaide

-0.65

NRS

-0.65

 Ezek

-0.65

ontent

-0.64

 murd

-0.63

anski

-0.63

externalActionCode

-0.63

POSITIVE LOGITS

ieval

0.70

 Tropical

0.68

alde

0.65

matically

0.65

arthed

0.65

ently

0.65

lish

0.65

events

0.64

verend

0.63

Reviewer

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.