INDEX

Explanations

actions and physical interactions between characters

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

Implies a slight movement or gesture of assent

np_acts-logits-general · gemini-2.0-flash

physical gestures or slight movements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 AssemblyCulture

-0.78

contentLoaded

-0.66

 Roskov

-0.63

 صوتيه

-0.63

 المعيارى

-0.62

 disambiguazione

-0.61

 ModelExpression

-0.60

twimg

-0.59

 <=",

-0.59

 незавершена

-0.58

POSITIVE LOGITS

 slightly

0.78

slightly

0.69

 fraction

0.62

 leggermente

0.60

 slight

0.59

Slight

0.58

 légèrement

0.58

 ligeramente

0.57

 Slight

0.56

fraction

0.53

Activations Density 0.101%

actions and physical interactions between characters

Implies a slight movement or gesture of assent

physical gestures or slight movements

No Comments

No Known Activations