INDEX

Explanations

directives related to accessing components in programming contexts

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

access to results

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

 propOrder

-0.77

NameInMap

-0.70

CloseOperation

-0.66

Parcelize

-0.64

 referenties

-0.63

 ویکی‌پدی

-0.63

 surla

-0.62

awtextra

-0.57

 ujednoznacz

-0.57

Hauptartikel

-0.57

POSITIVE LOGITS

 accesibles

0.51

argli

0.45

 needs

0.45

 need

0.44

 necesitamos

0.43

 infancia

0.42

 Keuangan

0.41

 literario

0.41

 access

0.40

 peindre

0.40

Activations Density 0.004%

directives related to accessing components in programming contexts

access to results

No Comments

No Known Activations