INDEX

Explanations

technical terms and function calls related to programming and data structures

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

haploinsufficiency and mathematical notation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

CppMethod

-0.63

 invokingState

-0.56

 IBOutlet

-0.53

Obrázky

-0.49

encodeWith

-0.45

adaptiveStyles

-0.44



-0.43

səhifə

-0.42

ANTLR

-0.42

 errand

-0.42

POSITIVE LOGITS

 autorytatywna

0.51

戬

0.48

Välislingid

0.45

NUMX

0.44

orical

0.42

 rotina

0.41

parametrize

0.40

(@"%@",

0.39

TokenNameLBRACE

0.39

shadowRadius

0.38

Activations Density 0.002%

technical terms and function calls related to programming and data structures

haploinsufficiency and mathematical notation

No Comments

No Known Activations