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

 Olsen

-0.76

iencies

-0.69

ÃŃn

-0.69

 Moder

-0.66

ãģ¦

-0.64

 Klein

-0.62

cair

-0.62

 Principle

-0.62

 Benson

-0.61

SPONSORED

-0.60

POSITIVE LOGITS

quit

0.68

stroke

0.67

ety

0.66

COLOR

0.62

ports

0.61

 tongues

0.60

uild

0.59

Gam

0.59

gam

0.59

cpu

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.