INDEX

Explanations

words and phrases indicating importance or significance

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

most important/desirable/appropriate

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 apparently

-0.72

 evidently

-0.65

 supposedly

-0.63

apparently

-0.62

 presumably

-0.62

 reportedly

-0.61

 Apparently

-0.59

どうやら

-0.58

presumably

-0.57

 allegedly

-0.55

POSITIVE LOGITS

 самый

0.49

 wichtigste

0.48

一番

0.48

 самой

0.47

最も

0.46

 самая

0.44

 meilleures

0.44

 gdyby

0.43

 safest

0.43

 wichtigsten

0.43

Activations Density 0.055%

words and phrases indicating importance or significance

most important/desirable/appropriate

No Comments

No Known Activations