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

 parach

-0.73

 Mage

-0.67

 blaster

-0.66

llah

-0.63

 slic

-0.63

erial

-0.63

 flyers

-0.63

 rider

-0.62

idav

-0.62

spr

-0.61

POSITIVE LOGITS

levard

0.69

emet

0.68

ogh

0.67

imore

0.67

ottesville

0.65

ALT

0.63

EMP

0.61

Js

0.60

uned

0.60

leground

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.