INDEX

Explanations

programming concepts related to event listeners and their management

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

event handling unsubscribe

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

AndEndTag

-0.56

verifyException

-0.48

 propOrder

-0.48

Oby

-0.45

 Taktlose

-0.41

исленность

-0.40

 EconPapers

-0.40

VYMaps

-0.39

IDAY

-0.39

 AppCompatTheme

-0.39

POSITIVE LOGITS

 pemasangan

0.39

avits

0.39

 Stel

0.37

getKeyCode

0.37

WriteBarrier

0.36

 procédures

0.36

 defaultstate

0.35

ricians

0.34

InputBorder

0.34

Mechanisms

0.34

Activations Density 0.031%

programming concepts related to event listeners and their management

event handling unsubscribe

No Comments

No Known Activations