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

-0.91

lish

-0.80

thal

-0.75

inas

-0.74

 è£ıç

-0.72

lishing

-0.71

swers

-0.71

hap

-0.71

ummer

-0.70

izabeth

-0.70

POSITIVE LOGITS

 helicop

0.79

 cryst

0.78

 challeng

0.78

 coefficients

0.75

 comr

0.71

 Niet

0.69

 prin

0.69

 slic

0.68

 streng

0.67

 incent

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.