INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

bush

-0.76

rities

-0.70

Thom

-0.69

ris

-0.68

cius

-0.67

conserv

-0.66

pec

-0.66

ELS

-0.66

ocl

-0.65

POSITIVE LOGITS

asta

0.80

 martyr

0.75

 aggro

0.73

 overload

0.71

 flank

0.69

Khe

0.68

 Torrent

0.67

 asteroids

0.66

 ambush

0.66

 responsibly

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.