INDEX

Explanations

phrases or structures that indicate a question is being asked

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

"question"

np_acts-logits-general · gemini-2.0-flash

introduces a question

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portale

-0.58

↴

-0.46

SBATCH

-0.42

بالإنجليزية

-0.42

bkz

-0.41

Mae

-0.39

FMC

-0.39

-0.38

ichy

-0.38

Lai

-0.38

POSITIVE LOGITS

 question

2.13

 Question

2.02

 questions

1.99

Question

1.91

 Questions

1.88

question

1.83

Questions

1.80

questions

1.78

 QUESTION

1.77

 QUESTIONS

1.70

Activations Density 0.115%

phrases or structures that indicate a question is being asked

"question"

introduces a question

No Comments

No Known Activations