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

spection

-0.71

 retri

-0.69

unique

-0.66

 arri

-0.65

accessible

-0.64

idge

-0.63

obs

-0.63

 fitt

-0.63

arta

-0.63

powered

-0.62

POSITIVE LOGITS

 Shadows

0.71

 Vulkan

0.69

ENCY

0.69

EMENT

0.66

ITNESS

0.65

UE

0.65

REAM

0.65

SQ

0.64

CNS

0.63

Shadow

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.