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

license

-0.71

LIC

-0.68

 Morsi

-0.66

 Mubarak

-0.64

AIR

-0.60

 Pose

-0.59

©¶æ

-0.57

 Mirage

-0.57

etheless

-0.57

paio

-0.57

POSITIVE LOGITS

agher

0.75

rington

0.74

der

0.71

rf

0.70

np

0.69

agar

0.68

down

0.67

nor

0.67

gp

0.66

fal

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.