INDEX

Explanations

keywords and phrases related to actions and activities

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

Follows an "Action" label, title, or column

np_acts-logits-general · gemini-2.0-flash

action

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

GEBURTSDATUM

-0.84

 nahilalakip

-0.59

insee

-0.55

 Wachs

-0.54

 Actual

-0.53

]--;

-0.53

rzost

-0.52

 actual

-0.51

actual

-0.51

новништво

-0.50

POSITIVE LOGITS

を起こ

0.77

//

0.72

bootstrapcdn

0.69

packed

0.69

 plan

0.68

 taken

0.65

 afirm

0.65

 packed

0.64

plan

0.64

 performed

0.63

Activations Density 0.060%

keywords and phrases related to actions and activities

Follows an "Action" label, title, or column

action

No Comments

No Known Activations