INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

uay

-0.98

ansk

-0.78

igil

-0.78

encia

-0.74

bay

-0.74

ury

-0.72

urer

-0.72

hoe

-0.71

zon

-0.71

loo

-0.70

POSITIVE LOGITS

etheless

0.89

worldly

0.85

 Hamm

0.80

 Dick

0.79

CMS

0.75

cised

0.75

 Pric

0.74

ItemTracker

0.73

HHS

0.72

 Whedon

0.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.