INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Ops

-0.75

 Tome

-0.66

osi

-0.65

 weap

-0.65

 newsp

-0.65

 Ratt

-0.64

aganda

-0.64

Sund

-0.63

kus

-0.63

Econom

-0.63

POSITIVE LOGITS

quished

0.66

geist

0.64

rencies

0.64

fulness

0.63

 bystanders

0.63

mberg

0.62

aea

0.62

ģĸ

0.61

ousel

0.60

 rendered

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.