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

ktop

-0.74

 tipped

-0.64

)).

-0.63

 alternatively

-0.62

 Oral

-0.62

 overlapping

-0.61

 garn

-0.61

 Pearce

-0.60

 iodine

-0.60

 downs

-0.59

POSITIVE LOGITS

fox

0.81

DragonMagazine

0.80

hack

0.80

Hack

0.71

Movie

0.70

efe

0.69

beh

0.69

oother

0.69

ICLE

0.67

advertising

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.