INDEX

Explanations

references to specific programming functions and parameters

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

Code-related abbreviations (BOOST, FT, goog, NS, PDO)

np_acts-logits-general · gemini-2.0-flash

programming prefixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 שוליים

-0.84

Geplaatst

-0.73

labelledby

-0.66

//

-0.66

ToScroll

-0.66

 MenuView

-0.65

TagMode

-0.64

خصة

-0.63

ContentAlignment

-0.63

ToBounds

-0.63

POSITIVE LOGITS

ूट

0.51

'][$

0.50

州市

0.50

 punishable

0.48

Sutton

0.47

 Италијани

0.47

"]));

0.47

dbg

0.47

usec

0.47

ikkert

0.46

Activations Density 0.280%

references to specific programming functions and parameters

Code-related abbreviations (BOOST, FT, goog, NS, PDO)

programming prefixes

No Comments

No Known Activations