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

enna

-0.81

 Calculator

-0.72

orns

-0.72

urus

-0.71

 Cups

-0.69

 Fairy

-0.67

zig

-0.66

airo

-0.65

illions

-0.65

":"/

-0.64

POSITIVE LOGITS

oÄŁ

0.81

ļéĨĴ

0.71

©¶æ

0.69

 diversion

0.68

uyomi

0.67

 watering

0.67

 watered

0.67

 advocacy

0.64

 grievance

0.63

coh

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.