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

ipeg

-0.77

yu

-0.76

Ã§

-0.75

icip

-0.75

pai

-0.75

cil

-0.74

visor

-0.74

laus

-0.73

veland

-0.73

Sense

-0.72

POSITIVE LOGITS

 averaging

0.71

 miscar

0.67

 seizures

0.66

 fluids

0.65

 humming

0.64

 misdem

0.64

 departures

0.64

 abduct

0.63

 inquiries

0.63

 rocking

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.