INDEX

Explanations

occurrences of access modifiers and their associated functions in a programming context

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

public function

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

 FetchType

-0.59

NewUrlParser

-0.50

帖最后由

-0.43

 Czechos

-0.41

 queſta

-0.40

fromnode

-0.40

 rhestr

-0.39

akterysty

-0.39

sendLogPayload

-0.39

upaten

-0.38

POSITIVE LOGITS

 nahilalakip

0.51

BorderLayout

0.45

WindowConstants

0.40

SourceChecksum

0.40

WEBPACK

0.39

 initComponents

0.39

Saf

0.39

mergeFrom

0.39

ItemSelected

0.38

 XCTest

0.38

Activations Density 0.002%

occurrences of access modifiers and their associated functions in a programming context

public function

No Comments

No Known Activations