INDEX

Explanations

terms related to precision, organization, and classification in various contexts

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

mathematical questions

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

aarrggbb

-0.75

دانشنامهٔ

-0.67

########.

-0.64

 jsPsych

-0.59

 InputDecoration

-0.57

󰈻

-0.55

⁛

-0.55

஥

-0.55

<unused8>

-0.54

 GoogleContinue

-0.54

POSITIVE LOGITS

(&:

0.29

 enamorado

0.27

一番

0.27

исленность

0.27

igshid

0.26

 Italijani

0.25

 NSCoder

0.25

 ویکی‌پدیای

0.25

userAgent

0.24

 estés

0.24

Activations Density 0.009%

terms related to precision, organization, and classification in various contexts

mathematical questions

No Comments

No Known Activations