INDEX

Explanations

keywords related to data processing and organization, specifically in reporting and querying contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

pivots and queries

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

Negative Logits

enterOuterAlt

-0.62

LookAnd

-0.60

tagext

-0.51

onViewCreated

-0.50

ButterKnife

-0.49

 iprot

-0.47

 ExecuteAsync

-0.47

iedene

-0.45

:✨

-0.44

wendig

-0.43

POSITIVE LOGITS

 kasarigan

0.49

druid

0.46

 Druid

0.45

 druid

0.44

 linkovi

0.43

Demografie

0.42

Druid

0.40

chkin

0.38

 useRef

0.38

 annot

0.36

Activations Density 0.037%

keywords related to data processing and organization, specifically in reporting and querying contexts

pivots and queries

No Known Activations