INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

-0.79

abilia

-0.67

 Pablo

-0.66

 Calais

-0.66

webkit

-0.66

Af

-0.65

%%%%

-0.64

oof

-0.63

 Valiant

-0.62

 Caval

-0.61

POSITIVE LOGITS

psey

0.73

RIPT

0.73

owship

0.71

meier

0.69

eon

0.64

ormon

0.63

anke

0.63

[*]

0.63

stall

0.63

ĻĤ

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.