INDEX

Explanations

mathematical assignments and operational definitions

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

is followed by variable definitions or descriptions

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

Portail

-0.57

醐

-0.56

 ragaz

-0.47

Definición

-0.46

 répartition

-0.45

 niedersachsen

-0.45

 Consolidation

-0.44

 Shand

-0.43

chtet

-0.43

Atsauces

-0.43

POSITIVE LOGITS

<_>

0.56

[*]

0.51

 ostavi

0.48

(_.

0.46

ViewFeatures

0.46

 resourceCulture

0.42

 صوتيه

0.42

Diweddarwch

0.42

 فريبيس

0.40

$_[

0.40

Activations Density 0.033%

mathematical assignments and operational definitions

is followed by variable definitions or descriptions

No Comments

No Known Activations