INDEX

Explanations

patterns related to data structuring and attribute definitions in code

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

numbers and symbols

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

 للاسماء

-0.92

 ſind

-0.84

новништво

-0.80

 ―――――

-0.79

 laſſen

-0.75

 verſch

-0.75

ſicht

-0.75

majánló

-0.75

InputBorder

-0.74

 ་་

-0.73

POSITIVE LOGITS

 setting

0.34

 whatever

0.32

 presentación

0.31

 fantasía

0.30

 estaremos

0.30

 prefi

0.29

 kurzen

0.29

 podremos

0.29

Activations Density 0.075%

patterns related to data structuring and attribute definitions in code

numbers and symbols

No Comments

No Known Activations