INDEX

Explanations

instances of questioning and interrogation, particularly in a legal or formal context

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

Words/questions following a question

np_acts-logits-general · gemini-2.0-flash

asking questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 فريبيس

-0.76

 للمعارف

-0.65

RenderAtEndOf

-0.61

HttpPut

-0.60

AddTagHelper

-0.57

 rowspan

-0.56

 ddelweddau

-0.52

 محفوظة

-0.49

 Verfügung

-0.48

CppMethod

-0.48

POSITIVE LOGITS

ask

2.53

 asked

2.38

 asks

2.33

 asking

2.28

Ask

2.21

Ask

2.14

asked

1.97

 Asking

1.95

Asking

1.93

ASK

1.91

Activations Density 0.369%

instances of questioning and interrogation, particularly in a legal or formal context

Words/questions following a question

asking questions

No Comments

No Known Activations