INDEX

Explanations

comments and annotations in code

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

starting conversations or code comments

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

出版年

-0.49

principalTable

-0.47

Espèce

-0.45



-0.43

hObject

-0.42

Gön

-0.41

 ویکی‌پدیا

-0.40

OrNull

-0.39

verwijspagina

-0.37

Atsauces

-0.36

POSITIVE LOGITS

transQ

0.50

垂

0.45

 kasarigan

0.45

 Penetration

0.43

StyleSheet

0.43

帖最后由

0.42

vrons

0.42

互

0.42

 stimmen

0.41

SEVERE

0.41

Activations Density 0.011%

comments and annotations in code

starting conversations or code comments

No Comments

No Known Activations