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

displayText

-0.94

vernment

-0.90

}}}

-0.87

staking

-0.83

thur

-0.75

 myster

-0.71

éĸ

-0.70

swer

-0.69

ħĭ

-0.69

Reviewer

-0.68

POSITIVE LOGITS

osuke

0.76

 Bened

0.68

 Catal

0.67

ows

0.63

Bus

0.62

BER

0.60

 Theresa

0.59

 Britons

0.59

 Bild

0.57

pec

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.