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

utenberg

-0.86

displayText

-0.80

arthed

-0.75

abus

-0.68

udic

-0.67

fee

-0.67

 guiActiveUnfocused

-0.66

ĸ

-0.65

adra

-0.64

dict

-0.64

POSITIVE LOGITS

 cheeks

0.65

 coinc

0.64

enny

0.61

ANCE

0.60

 preferably

0.60

 cheek

0.60

handedly

0.60

 Startup

0.59

 phrases

0.58

 ende

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.