INDEX

Explanations

structured code elements, specifically focusing on code syntax and formatting

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

Code snippets with curly brackets

np_acts-logits-general · gemini-2.0-flash

between the

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵

-1.32

<h6>

-0.47

ணை

-0.46

<h5>

-0.46

ítmény

-0.44

\&

-0.43

 chóng

-0.43

lasser

-0.43

daction

-0.42

MAXN

-0.42

POSITIVE LOGITS

 AspNetCore

0.82

 }}$}

0.77

titleMargin

0.73

 متعلقه

0.72

ValueStyle

0.70

 ligiloj

0.70

 فريبيس

0.68

</caption>

0.67

 wireType

0.67

 ivelany

0.67

Activations Density 0.109%

structured code elements, specifically focusing on code syntax and formatting

Code snippets with curly brackets

between the

No Comments

No Known Activations