INDEX

Explanations

specific introductory phrases used in text, possibly to catch attention or indicate a transition

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "The"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Ò

-0.72

ãĥĺ

-0.68

rade

-0.64

dk

-0.63

 theirs

-0.63

.''

-0.62

 exceeds

-0.61

plet

-0.61

.<

-0.61

âĵĺ

-0.61

POSITIVE LOGITS

odore

1.37

 Basics

1.32

 gist

1.28

resa

1.27

 Problem

1.26

oret

1.23

ories

1.17

 simplest

1.14

 irony

1.08

ory

1.07

Activations Density 0.313%

specific introductory phrases used in text, possibly to catch attention or indicate a transition

occurrences of the word "The"

No Comments

No Known Activations