INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iasis

-0.74

wob

-0.73

 cane

-0.72

Appearances

-0.70

rection

-0.69

âĶĢâĶĢâĶĢâĶĢ

-0.69

 duct

-0.68

 actionGroup

-0.67

mouth

-0.65

raft

-0.65

POSITIVE LOGITS

iron

0.69

ELY

0.69

ĨĴ

0.69

Ĥİ

0.68

memory

0.67

dimension

0.67

atom

0.66

APD

0.65

liga

0.62

Stock

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.