INDEX

Explanations

expressions of personal opinions and recommendations regarding literature

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

"I" followed by opinion verbs

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



-0.64

rungsseite

-0.57

 فريبيس

-0.53

Дерекк

-0.52

 doInBackground

-0.51

parsedMessage

-0.50

 esternos

-0.50

 GetEnumerator

-0.49

#+#

-0.49

olverine

-0.49

POSITIVE LOGITS

VolleyError

0.37

 book

0.34

 frutto

0.32

 Inhalts

0.31

 Zustimmung

0.30

amitié

0.30

 penilaian

0.30

 SDLK

0.29

Genre

0.29

ंदीखरीदारी

0.29

Activations Density 0.037%

expressions of personal opinions and recommendations regarding literature

"I" followed by opinion verbs

No Comments

No Known Activations