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

yon

-0.76

terness

-0.73

separ

-0.72

©¶æ

-0.69

bek

-0.69

nov

-0.69

cas

-0.69

might

-0.68

 Entreprene

-0.68

may

-0.67

POSITIVE LOGITS

abase

0.69

Sut

0.67

ilial

0.67

 mutated

0.65

 mole

0.61

 composition

0.60

 asbestos

0.60

 ital

0.58

 systemic

0.58

FIELD

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.