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

Ĥİ

-0.84

ebus

-0.80

amas

-0.76

 selfies

-0.75

å§

-0.74

awei

-0.74

lash

-0.73

hiba

-0.73

 showc

-0.73

ribute

-0.72

POSITIVE LOGITS

 Secondly

0.76

 Definition

0.75

 Flavoring

0.73

 Accordingly

0.72

 Particularly

0.72

 Suppose

0.71

 Rutherford

0.70

 Universities

0.70

Definition

0.70

 Lawyers

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.