INDEX

Explanations

frequently used verbs and their attributes in a technical context

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

actions and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

########.

-0.44

AnimationsModule

-0.38

éviter

-0.36

openConnection

-0.35

 виправивши

-0.35

 layui

-0.35

 mathematicians

-0.33

 Laus

-0.33

 kinderen

-0.33

 marino

-0.33

POSITIVE LOGITS

tvguidetime

0.65

ConstraintMaker

0.63

 kasarigan

0.54

 Италијани

0.53

 متعلقه

0.53

Ծանոթ

0.49

 незавершена

0.47

存于互联网档案馆

0.47

 neceff

0.46

verifyException

0.46

Activations Density 0.054%

frequently used verbs and their attributes in a technical context

actions and states

No Comments

No Known Activations