INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

-0.83

isha

-0.77

istered

-0.69

ered

-0.68

eka

-0.68

vern

-0.67

eb

-0.66

bery

-0.65

ich

-0.65

ksh

-0.64

POSITIVE LOGITS

ailability

0.79

iments

0.71

":-

0.68

Hew

0.68

 WATCHED

0.67

\\\\\\\\

0.67

 semantics

0.66

acity

0.65

âĢ¢âĢ¢âĢ¢âĢ¢

0.63

roup

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.