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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 VIDEOS

-0.82

eredith

-0.76

 guiActiveUnfocused

-0.74

 Flavoring

-0.74

 Samar

-0.73

iola

-0.73

 Philipp

-0.72

 Coleman

-0.71

 Cheong

-0.70

 Calvin

-0.70

POSITIVE LOGITS

 hypot

0.71

sov

0.70

ities

0.66

 cull

0.66

 redes

0.64

wikipedia

0.63

 confir

0.63

 unmanned

0.62

aft

0.62

 between

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.