INDEX

Explanations

code-related structures and definitions, particularly focusing on data types and method parameters

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

Content type or media type specifications

np_acts-logits-general · gemini-2.0-flash

content type and media type parsing

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

crtc

-0.42

 Lucky

-0.40

ge

-0.40

ModelAttribute

-0.38

額

-0.38

แต่ง

-0.37

ното

-0.37

 pull

-0.37

who

-0.37

 >=",

-0.37

POSITIVE LOGITS

 TextInputType

0.96

 purpoſe

0.86

Jeografia

0.81

styleType

0.80

 EClass

0.80

 MIME

0.80

nologies

0.79

 /\.(

0.79

ArrowToggle

0.78

Geplaatst

0.77

Activations Density 0.501%

code-related structures and definitions, particularly focusing on data types and method parameters

Content type or media type specifications

content type and media type parsing

No Comments

No Known Activations