INDEX

Explanations

proper nouns related to people involved in various narratives or stories

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

last names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 Infórmanos

-1.02

 resourceCulture

-0.92

EndGlobalSection

-0.90

rungsseite

-0.89

sizeCache

-0.88

➯

-0.85

 disambiguazione

-0.85

𐑥

-0.83

 <>",

-0.82

﹧

-0.82

POSITIVE LOGITS

 also

0.32

 enggak

0.28

ان

0.27

 pulito

0.27

 blessé

0.26

 quindi

0.25

 âgé

0.25

 hence

0.25

 then

0.23

 hablado

0.23

Activations Density 0.138%

proper nouns related to people involved in various narratives or stories

last names

No Comments

No Known Activations