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

kefeller

-0.78

phia

-0.76

 skelet

-0.70

sen

-0.68

naire

-0.67

aucus

-0.64

 importantly

-0.61

higher

-0.61

 dare

-0.61

MAP

-0.61

POSITIVE LOGITS

iHUD

0.70

 Laden

0.69

 crates

0.68

Obj

0.67

evil

0.67

 Parenthood

0.64

bugs

0.63

ãĥĥ

0.60

 Anarchy

0.60

bara

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.