INDEX

Explanations

terms related to 'voice' and 'speech' technologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ConstraintMaker

-0.88

rungsseite

-0.83

RunAsync

-0.83

GEBURTSDATUM

-0.81

dafx

-0.78

tagHelperRunner

-0.78

 EconPapers

-0.77

 الرياضيه

-0.77

expandindo

-0.75

期刊论文

-0.73

POSITIVE LOGITS

 voices

0.68

mails

0.67

 voice

0.66

 Voices

0.65

mail

0.64

Voices

0.61

 Voice

0.57

 mail

0.57

 Stimmen

0.57

voices

0.56

Activations Density 0.059%

terms related to 'voice' and 'speech' technologies

No Comments

No Known Activations