INDEX

Explanations

programming-related terms and operations in code snippets

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

<start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

fromnode

-0.41

 XCTest

-0.35

 Replacement

-0.35

 зави

-0.34

겠

-0.33

Replace

-0.32

uxxxx

-0.32

ifikationer

-0.32

 Fruit

-0.32

łania

-0.32

POSITIVE LOGITS

MethodManager

0.58

setVerticalGroup

0.53

RTLR

0.52

 ffilmiau

0.48

Бахар

0.48

 hObject

0.47

 <=",

0.46

inSlope

0.45

RTLI

0.43

IVEREF

0.43

Activations Density 0.104%

programming-related terms and operations in code snippets

<start_of_turn> user

No Comments

No Known Activations