INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ORE

-0.80

Rae

-0.71

HRC

-0.70

uba

-0.68

ITH

-0.68

 TRUMP

-0.67

Jed

-0.66

netflix

-0.65

 Wade

-0.64

ovation

-0.64

POSITIVE LOGITS

zzi

0.65

 marrow

0.65

 barr

0.64

 sewage

0.63

umb

0.63

ennett

0.62

 glim

0.62

 fluorescent

0.61

imens

0.61

 stre

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.