INDEX

Explanations

structural code elements and classes in programming content

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

Code snippets or programming-related text

np_acts-logits-general · gemini-2.0-flash

time:

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

<u>

-0.47

<sub>

-0.45

 Arquivado

-0.43

出版年

-0.42

 Offisielt

-0.42

ValueStyle

-0.40

fű

-0.40

 vérit

-0.40

گاهی

-0.39

();

-0.39

POSITIVE LOGITS

1.57

↵

0.90

 betweenstory

0.82

سطس

0.76

TintMode

0.75

Становништво

0.67

+#+#

0.65

posedge

0.63

omitempty

0.63

KommentareTeilen

0.61

Activations Density 0.020%

structural code elements and classes in programming content

Code snippets or programming-related text

time:

No Comments

No Known Activations