INDEX

Explanations

expressions of gratitude and appreciation

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

expresses appreciation or positive 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

 queſta

-0.60

 الرياضيه

-0.57

 informée

-0.57

 FetchType

-0.55

NewUrlParser

-0.54

HasAnnotation

-0.52

RTLD

-0.51

 juſ

-0.51

 leaſt

-0.50

 smtplib

-0.49

POSITIVE LOGITS

AndEndTag

0.42

openzeppelin

0.41

 commend

0.41

comments

0.40

 compliment

0.40

 praise

0.38

comment

0.38

lovely

0.38

testify

0.38

 commendation

0.36

Activations Density 0.042%

expressions of gratitude and appreciation

expresses appreciation or positive comments

No Comments

No Known Activations