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

 ceilings

-0.66

 SHARES

-0.64

 births

-0.63

Introdu

-0.62

pid

-0.61

Driver

-0.61

 bedrooms

-0.61

 Pigs

-0.61

 Tune

-0.60

IDES

-0.60

POSITIVE LOGITS

theless

0.74

ulla

0.73

urations

0.71

arcity

0.70

allery

0.69

 vice

0.69

algia

0.67

urga

0.66

earcher

0.66

ukong

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.