INDEX

Explanations

expressions that introduce examples or clarifications

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

Introductory asides/disclaimers

np_acts-logits-general · gemini-2.0-flash

supplementary notes and disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

__(/*!

-0.69

 الحره

-0.68

 dalamnya

-0.62

ukkig

-0.61

 chiaramente

-0.61

 Administrativna

-0.61

]=>

-0.60

يميديا

-0.59

 capaces

-0.59

indd

-0.58

POSITIVE LOGITS

FYI

0.97

 note

0.97

余談

0.95

FYI

0.93

 siden

0.92

 clarification

0.87

FWIW

0.79

顺便

0.79

 disclaimer

0.78

 quick

0.78

Activations Density 0.283%

expressions that introduce examples or clarifications

Introductory asides/disclaimers

supplementary notes and disclaimers

No Comments

No Known Activations