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

doms

-0.74

stood

-0.73

edin

-0.73

PsyNetMessage

-0.71

 Babel

-0.71

Graph

-0.69

riers

-0.69

 è£ıè

-0.69

 Consumption

-0.68

Container

-0.68

POSITIVE LOGITS

 eleph

0.86

fug

0.71

 coup

0.68

htaking

0.67

 disarm

0.67

 irresist

0.66

mag

0.64

tum

0.63

 bald

0.63

 restoration

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.