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

\\\\\\\\\\\\\\\\

-0.77

 Phelps

-0.73

 laun

-0.68

 Greenland

-0.67

 mayor

-0.63

astical

-0.63

 padd

-0.62

 mayors

-0.62

boats

-0.61

 Parks

-0.59

POSITIVE LOGITS

widget

0.76

andra

0.74

cious

0.72

 Franch

0.70

imester

0.67

ihar

0.66

 Crunch

0.64

malink

0.63

Viz

0.63

 ingestion

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.