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

flies

-0.79

comfort

-0.73

script

-0.71

personal

-0.70

wered

-0.68

edited

-0.67

functional

-0.67

Alias

-0.65

ãĥĺ

-0.65

cultural

-0.64

POSITIVE LOGITS

 Â©

0.74

adj

0.70

lihood

0.66

NOW

0.63

ASS

0.63

ENE

0.63

 Finally

0.62

ORE

0.62

 Franch

0.62

 tampering

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.