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

ngth

-1.04

hower

-0.70

bons

-0.67

*/(

-0.66

 Panzer

-0.66

rift

-0.65

wagen

-0.65

 mine

-0.64

abolic

-0.64

uple

-0.63

POSITIVE LOGITS

 Bitcoins

0.66

uploads

0.65

 Maryland

0.65

 Sinai

0.64

chester

0.64

 Barcelona

0.63

Tah

0.60

 Bloomberg

0.60

 Cards

0.60

 Qualcomm

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.