INDEX

Explanations

phrases indicating the presence of questions or inquiries

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

asking 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

 queſta

-0.64

 varandra

-0.55

 dezelve

-0.54

migrationBuilder

-0.54

::_('

-0.53

 ioutil

-0.53

 NSCoder

-0.53

 desmotivaciones

-0.53

 houſe

-0.52

ſelves

-0.51

POSITIVE LOGITS

 questions

0.52

 Question

0.51

 Questions

0.48

 question

0.47

 QUESTIONS

0.47

 questioned

0.46

 asked

0.46

 Frage

0.46

Question

0.44

questions

0.43

Activations Density 0.085%

phrases indicating the presence of questions or inquiries

asking questions

No Comments

No Known Activations