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

´

-0.71

iatus

-0.71

zac

-0.69

¬

-0.69

ĳ

-0.69

ļ

-0.67

 Tasmania

-0.67

 Factor

-0.67

Invalid

-0.66

ŀ

-0.66

POSITIVE LOGITS

 leather

0.77

vine

0.75

 tempo

0.72

isites

0.68

cloth

0.68

anguage

0.63

ufact

0.63

 cloth

0.62

ktop

0.62

veh

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.