INDEX

Explanations

references to actions and adventurous activities

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

"action" or "actionable"

np_acts-logits-general · gemini-2.0-flash

action and adventure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 nahilalakip

-0.87

 GenerationType

-0.74

 дописавши

-0.64

存于互联网档案馆

-0.62

ConstraintMaker

-0.61

הערות

-0.61

 ostavi

-0.60

 useAppContext

-0.59

Rujukan

-0.57

-------

-0.57

POSITIVE LOGITS

getAction

0.67

 afirm

0.66

 Actions

0.66

 UIAlert

0.65

 taken

0.65

ToAction

0.65

 packed

0.63

plan

0.63

 ACTION

0.63

packed

0.63

Activations Density 0.122%

references to actions and adventurous activities

"action" or "actionable"

action and adventure

No Comments

No Known Activations