INDEX

Explanations

include statements in programming or markup languages

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

Code or imports

np_acts-logits-general · gemini-2.0-flash

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

OGND

-0.80

 كومونز

-0.75



-0.71

setVerticalGroup

-0.66

 kasarigan

-0.65

 AssemblyTitle

-0.63

 للاسماء

-0.63

Autoritní

-0.62

 يتيمه

-0.60

 EconPapers

-0.60

POSITIVE LOGITS

 Google

0.50

Google

0.40

Sha

0.40

Che

0.40

 extra

0.39

 google

0.38

 especially

0.38

math

0.37

 time

0.37

sha

0.35

Activations Density 0.033%

include statements in programming or markup languages

Code or imports

No Comments

No Known Activations