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

 Foster

-0.71

ypes

-0.69

peak

-0.69

anger

-0.68

 Immunity

-0.68

 Crafting

-0.67

 Crossing

-0.66

rosso

-0.65

 Unreal

-0.64

nuts

-0.64

POSITIVE LOGITS

issance

0.81

zens

0.75

htar

0.72

 mathemat

0.68

 occupant

0.67

licted

0.67

 includ

0.64

umbai

0.64

FAULT

0.64

*/

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.