INDEX

Explanations

references to laughter or laughing

oai_token-act-pair · gpt-3.5-turbo

instances of the word "laugh" and its variations, indicating a focus on humor and laughter

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

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

struct

-0.73

ģ

-0.71

des

-0.71

area

-0.67

 Stra

-0.65

 Prec

-0.64

di

-0.63

mi

-0.63

Dri

-0.63

abling

-0.62

POSITIVE LOGITS

 laugh

3.95

 chuckle

2.83

 laughs

2.10

 laughter

2.10

 laughing

1.99

 smile

1.91

 joke

1.84

 grin

1.79

 Laugh

1.77

laugh

1.75

Activations Density 0.010%

references to laughter or laughing

instances of the word "laugh" and its variations, indicating a focus on humor and laughter

No Comments

No Known Activations