INDEX

Explanations

second person pronouns indicating the reader, specifically focusing on instructions or recommendations

oai_token-act-pair · gpt-3.5-turbo

references to the pronoun "you."

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

¿½

-0.93

forms

-0.64

pires

-0.64

Contents

-0.61

 resumes

-0.60

lights

-0.57

itol

-0.56

 newcom

-0.56

ingen

-0.55

assemb

-0.54

POSITIVE LOGITS

're

1.93

've

1.61

'll

1.33

 intend

1.32

 want

1.30

are

1.25

 haven

1.23

 aren

1.23

 wanna

1.22

 prefer

1.15

Activations Density 0.235%

second person pronouns indicating the reader, specifically focusing on instructions or recommendations

references to the pronoun "you."

No Comments

No Known Activations