INDEX

Explanations

questions and prompts encouraging user interaction and feedback

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

Followed by questions or requests for feedback

np_acts-logits-general · gemini-2.0-flash

comments and suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

HtmlAttribute

-0.51

sidemargin

-0.50

FormTagHelper

-0.48

ruptedException

-0.47

ParallelGroup

-0.46

 ausges

-0.46

 wireType

-0.45

 TestBed

-0.45

IntoConstraints

-0.45

idenav

-0.44

POSITIVE LOGITS

 comments

0.89

 comment

0.84

 Comment

0.78

comment

0.77

Comment

0.75

 Comments

0.74

 commenting

0.74

comments

0.71

 COMMENT

0.69

留言

0.67

Activations Density 0.105%

questions and prompts encouraging user interaction and feedback

Followed by questions or requests for feedback

comments and suggestions

No Comments

No Known Activations