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

WB

-0.75

ocene

-0.75

EA

-0.74

JUST

-0.73

Su

-0.70

UFC

-0.69

KO

-0.68

IFA

-0.68

OWS

-0.67

orus

-0.66

POSITIVE LOGITS

 metab

0.70

 congest

0.69

conservancy

0.66

 edge

0.66

 compr

0.66

nance

0.66

izont

0.65

hub

0.65

 Babel

0.64

 inclined

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.