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

agra

-0.87

 amnesty

-0.79

nesty

-0.70

olid

-0.70

wright

-0.69

 legisl

-0.69

oun

-0.67

berra

-0.66

onet

-0.66

ĸļ

-0.66

POSITIVE LOGITS

 Situation

0.79

................................................................

0.78

 Gamb

0.76

ItemThumbnailImage

0.75

å§«

0.69

Bone

0.68

 Plot

0.68

Reply

0.68

 Zombies

0.67

Synopsis

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.