INDEX

Explanations

elements related to visual representation and scheduling features in documents

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

Tokens after image file extensions

np_acts-logits-general · gemini-2.0-flash

numbers and vs comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Geset

-0.39

 Potencia

-0.38

 ролях

-0.38

 geomé

-0.37

 Zuschauer

-0.37

 paſſ

-0.37

 cauſe

-0.36

VIAF

-0.36

 kanker

-0.35

 elástica

-0.35

POSITIVE LOGITS

_-_

0.71

transQ

0.70

 betweenstory

0.68

FINAL

0.66

awtextra

0.61

 FINAL

0.60

final

0.60

 defaultstate

0.58

Final

0.58

Activations Density 0.678%

elements related to visual representation and scheduling features in documents

Tokens after image file extensions

numbers and vs comparisons

No Comments

No Known Activations