INDEX

Explanations

references to data, methodologies, and detailed descriptions in academic or research contexts

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

Prepositions/conjunctions that introduce explanations or justifications

np_acts-logits-general · gemini-2.0-flash

expressed as purpose or reason

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

 utafitiHapana

-0.70

WireFormatLite

-0.68

 للمعارف

-0.66

تقاوى

-0.64

ロウィン

-0.63

StoryboardSegue

-0.63

 nahilalakip

-0.62

richTextPanel

-0.60

 AspNetCore

-0.60

ScopeManager

-0.60

POSITIVE LOGITS

 because

1.18

because

1.04

Because

0.93

 porque

0.92

 Because

0.91

 omdat

0.88

 BECAUSE

0.85

因为

0.81

 becau

0.77

 karena

0.76

Activations Density 0.805%

references to data, methodologies, and detailed descriptions in academic or research contexts

Prepositions/conjunctions that introduce explanations or justifications

expressed as purpose or reason

No Comments

No Known Activations