INDEX

Explanations

terms related to audio and listening activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-0.66

UEZ

-0.55

блица

-0.52

eyed

-0.50

LookUp

-0.48

 luce

-0.48

 optical

-0.48

ніципалі

-0.47

 maler

-0.46

 Inspect

-0.46

POSITIVE LOGITS

 listeners

1.40

 audio

1.33

 listen

1.33

 listener

1.32

 listened

1.29

 Listen

1.28

 listening

1.24

 Audio

1.24

Audio

1.17

 hear

1.17

Activations Density 0.365%

terms related to audio and listening activities

No Comments

No Known Activations

terms related to audio and listening activities

No Comments

No Known Activations