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

Ĥİ

-0.73

 Grounds

-0.70

TextColor

-0.70

PLA

-0.68

CHA

-0.68

ħĭ

-0.66

Rogue

-0.65

eus

-0.63

Words

-0.63

 AUTH

-0.62

POSITIVE LOGITS

ormonal

0.69

omsday

0.69

ibur

0.67

atom

0.67

acion

0.66

"'

0.66

pora

0.62

 Ashton

0.62

=-=-=-=-

0.61

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.