INDEX

Explanations

instances of the word "involved" and its variations, indicating participation or engagement in various contexts

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

"involved in"

np_acts-logits-general · gemini-2.0-flash

being involved in

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

-0.56

 naturales

-0.56

 alimentaires

-0.56

rceil

-0.54

ers

-0.52

 Domini

-0.52

اء

-0.52

esez

-0.51

atouille

-0.50

 plano

-0.50

POSITIVE LOGITS

 involve

0.74

InstanceState

0.73

rungsseite

0.72

tvguidetime

0.71

 involved

0.71

UseVisualStyle

0.69

 Involved

0.69

=$?

0.66

 engaged

0.64

hoea

0.64

Activations Density 0.092%

instances of the word "involved" and its variations, indicating participation or engagement in various contexts

"involved in"

being involved in

No Comments

No Known Activations