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

 faint

-0.67

 authenticated

-0.65

 credential

-0.64

meter

-0.62

 disinfect

-0.61

 doping

-0.61

 awoken

-0.60

hatt

-0.59

ogical

-0.59

 thumb

-0.59

POSITIVE LOGITS

enegger

0.83

ean

0.77

cko

0.77

orno

0.74

olphin

0.73

Goo

0.73

Reviewer

0.69

 Jarvis

0.69

 guiActiveUnfocused

0.69

mir

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.