INDEX

Explanations

phrases related to inquiries and questions

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

Precedes or relates to questions

np_acts-logits-general · gemini-2.0-flash

asking and answering questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.60

äumt

-0.57

 للمعارف

-0.54

HttpPut

-0.52

Intérieur

-0.47

RenderAtEndOf

-0.46

 otomatig

-0.46

 rhestr

-0.44

ніципалі

-0.44

 Memoir

-0.43

POSITIVE LOGITS

 question

3.01

 questions

2.94

 Question

2.60

question

2.53

 Questions

2.48

Question

2.48

questions

2.46

Questions

2.42

 QUESTION

2.38

 QUESTIONS

2.30

Activations Density 0.500%

phrases related to inquiries and questions

Precedes or relates to questions

asking and answering questions

No Comments

No Known Activations