INDEX

Explanations

mentions of annotations in code

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

Followed by "Override"

np_acts-logits-general · gemini-2.0-flash

@Override annotation

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

 enter

-0.32

moveToFirst

-0.30

 appelez

-0.28

 لعب

-0.28

JOIN

-0.28

—

-0.28

AppCompatTheme

-0.27

łecz

-0.26

@[+][

-0.26

POSITIVE LOGITS

Override

0.84

payed

0.62

 Walkover

0.60

 Override

0.60

הערות

0.59

 voorbij

0.55

 dépass

0.55

verride

0.54

oned

0.54

 zijne

0.54

Activations Density 0.015%

mentions of annotations in code

Followed by "Override"

@Override annotation

No Comments

No Known Activations