INDEX

Explanations

phrases indicating recognition or accolades for individuals

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

"For" followed by a pronoun

np_acts-logits-general · gemini-2.0-flash

reason for mentioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

เอง

-0.43

 Gericht

-0.39

 comprob

-0.38

 Masyarakat

-0.38

comuna

-0.38

 saites

-0.37

 uLocal

-0.36

Française

-0.36

uchin

-0.36

 âgé

-0.35

POSITIVE LOGITS

 being

1.26

 having

0.99

being

0.92

Being

0.86

 Being

0.79

 BEING

0.77

having

0.75

 essere

0.73

 HAVING

0.71

 Мексичка

0.69

Activations Density 0.238%

phrases indicating recognition or accolades for individuals

"For" followed by a pronoun

reason for mentioning

No Comments

No Known Activations

phrases indicating recognition or accolades for individuals

"For" followed by a pronoun

reason for mentioning

No Comments

No Known Activations