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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flavoring

-0.69

ALLY

-0.60

ially

-0.59

 Sullivan

-0.59

LESS

-0.59

arya

-0.59

ribly

-0.59

aunted

-0.58

ELY

-0.58

 Oprah

-0.58

POSITIVE LOGITS

merce

0.82

emis

0.76

bay

0.76

ffield

0.73

 ende

0.72

onies

0.71

asters

0.69

fly

0.67

endars

0.66

south

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.