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

à¦

-0.77

iband

-0.70

tein

-0.70

opa

-0.68

 pedals

-0.68

ghai

-0.67

 brakes

-0.65

andowski

-0.65

tarian

-0.62

duino

-0.62

POSITIVE LOGITS

 corpus

0.74

 Fein

0.67

alde

0.67

 Hers

0.65

 Corpus

0.65

iche

0.64

 Neph

0.63

Fey

0.63

Leh

0.62

 paran

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.