INDEX

Explanations

words and phrases related to structured data and its interactions in queries

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

code and technical terms

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

 EconPapers

-0.67

rawDesc

-0.66

 '\\;'

-0.66

évaluateur

-0.66

 ब्रेकडाउन

-0.62

 виправивши

-0.60

ParallelGroup

-0.58

Personensuche

-0.58

contentLoaded

-0.58

sidemargin

-0.57

POSITIVE LOGITS

Referències

0.43

 ministère

0.38

Enllaços

0.33

Kaynakça

0.32

Fußball

0.32

 münd

0.31

 cuales

0.31

 obtenido

0.30

 Welt

0.30

失

0.30

Activations Density 0.398%

words and phrases related to structured data and its interactions in queries

code and technical terms

No Comments

No Known Activations