INDEX

Explanations

mentions of specific items, actions, or key concepts related to products, services, and experiences

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

before conjunctions

np_acts-logits-general · gemini-2.0-flash

your or yourself

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 оригіналу

-0.76

due

-0.73

Due

-0.70

whereas

-0.69

due

-0.68

 whereas

-0.66

 owing

-0.66

omyelitis

-0.65

hence

-0.64

 debido

-0.63

POSITIVE LOGITS

 yourself

1.32

yourself

0.94

 YOURSELF

0.90

 yourselves

0.86

 Yourself

0.81

 anytime

0.80

 your

0.79

 nhé

0.76

 preferably

0.75

 eens

0.75

Activations Density 0.425%

mentions of specific items, actions, or key concepts related to products, services, and experiences

before conjunctions

your or yourself

No Comments

No Known Activations