INDEX

Explanations

terms related to speech and voice recognition

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to speech recognition and its applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ruary

-0.76

 Soldiers

-0.70

EGA

-0.70

 Closing

-0.69

folio

-0.68

 Bourbon

-0.68

zona

-0.67

ģĸ

-0.67

 Enix

-0.67

rolet

-0.66

POSITIVE LOGITS

 spoken

0.96

 comprehension

0.93

 phon

0.90

 uttered

0.87

 overheard

0.86

gib

0.82

spe

0.82

bone

0.82

 deaf

0.81

 phrases

0.81

Activations Density 0.110%

terms related to speech and voice recognition

terms and phrases related to speech recognition and its applications

No Comments

No Known Activations