INDEX

Explanations

references to voices in various contexts, particularly focusing on authenticity and expression

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

"voice" or "voices"

np_acts-logits-general · gemini-2.0-flash

voice of

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

期刊论文

-0.71

 isNameExpr

-0.61

#+#

-0.59

ocarpus

-0.59

icitis

-0.58

Tembelea

-0.58

\}\\

-0.58

Datuak

-0.56

 Obispo

-0.56

tagHelperRunner

-0.54

POSITIVE LOGITS

 voice

1.57

 Voice

1.41

 voices

1.39

Voice

1.31

 VOICE

1.30

voice

1.30

 Voices

1.20

voices

1.17

VOICE

1.13

 voix

1.08

Activations Density 0.084%

references to voices in various contexts, particularly focusing on authenticity and expression

"voice" or "voices"

voice of

No Comments

No Known Activations