INDEX

Explanations

key programming and data structure terms related to object-oriented programming concepts

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

programming class names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.48

-0.43

-0.42

</strong>

-0.38

 west

-0.38

contentValues

-0.38

 east

-0.36

<eos>

-0.36

two

-0.36

-0.35

POSITIVE LOGITS

 ModelExpression

0.75

 wikipagina

0.71

 Wikiseite

0.70

ValueStyle

0.69

ghijklmnop

0.68

 Majefty

0.68

 Chriftian

0.68

 Perſ

0.67

 Houſe

0.65

iffance

0.65

Activations Density 0.071%

key programming and data structure terms related to object-oriented programming concepts

programming class names

No Comments

No Known Activations