INDEX

Explanations

technical terminology and descriptions related to processes and functions

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

Followed by verbs

np_acts-logits-general · gemini-2.0-flash

German phrases and technical construction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

-0.95

 betweenstory

-0.85

 فريبيس

-0.81

ьаж

-0.68

Personendaten

-0.67

DeleteBehavior

-0.63

 propOrder

-0.63

 للاسماء

-0.61

tagHelperRunner

-0.59

 ब्रेकडाउन

-0.59

POSITIVE LOGITS

 scarcity

0.40

ger

0.38

нки

0.36

san

0.35

tig

0.35

vit

0.35

openqa

0.34

 sanity

0.34

oty

0.34

gib

0.33

Activations Density 0.221%

technical terminology and descriptions related to processes and functions

Followed by verbs

German phrases and technical construction

No Comments

No Known Activations