INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

kin

-0.69

ilant

-0.68

opes

-0.67

lin

-0.67

 undercover

-0.65

LIN

-0.65

 Pastebin

-0.65

ope

-0.64

ophe

-0.64

ppard

-0.64

POSITIVE LOGITS

ãĥĺ

0.72

deb

0.70

ãĤ¼

0.69

asing

0.68

ãĤ¤

0.66

Winner

0.65

 Recession

0.63

folios

0.62

price

0.62

 Drawn

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.