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

 Gutenberg

-0.74

KP

-0.72

eering

-0.70

 Dragonbound

-0.68

 redu

-0.67

 Skydragon

-0.66

 Triumph

-0.65

Kaw

-0.65

 Might

-0.64

naire

-0.64

POSITIVE LOGITS

lein

0.73

endon

0.73

rued

0.72

Ħ¢

0.70

zbollah

0.70

cipled

0.69

dozen

0.68

actus

0.67

Cruz

0.66

ForgeModLoader

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.