INDEX

Explanations

phrases related to auditory perception, specifically hearing or being informed about something

oai_token-act-pair · gpt-3.5-turbo

variations of the word "hear" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

sis

-0.71

alias

-0.66

 Leap

-0.66

igsaw

-0.64

 Shrine

-0.63

istration

-0.63

isoft

-0.63

PHOTOS

-0.63

arcity

-0.63

orp

-0.61

POSITIVE LOGITS

 voices

0.98

 Heard

0.95

 Hear

0.84

 heard

0.82

 hear

0.81

 footsteps

0.81

 hearing

0.81

 louder

0.80

 aloud

0.78

 Hearing

0.77

Activations Density 0.048%

phrases related to auditory perception, specifically hearing or being informed about something

variations of the word "hear" and its derivatives

No Comments

No Known Activations