INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ONSORED

-0.67

 Matters

-0.66

Û

-0.63

arez

-0.61

letters

-0.60

haz

-0.59

 troll

-0.59

 Benn

-0.57

²¾

-0.57

 breath

-0.56

POSITIVE LOGITS

cens

0.90

ãĥķãĤ©

0.77

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

0.71

éĹĺ

0.70

owicz

0.68

utical

0.67

Streamer

0.66

paralle

0.66

assic

0.65

 Madagascar

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.