INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ived

-0.78

 surfing

-0.68

 protesting

-0.64

 upstream

-0.63

 coli

-0.62

dug

-0.61

 ducks

-0.60

assetsadobe

-0.60

apolis

-0.60

ousands

-0.59

POSITIVE LOGITS

Hour

0.77

ilst

0.75

66666666

0.73

Ã«

0.71

romeda

0.71

Dust

0.67

gaard

0.66

bite

0.66

ignty

0.66

OY

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.