INDEX

Explanations

details related to mortality and memory

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

"Ahead" or "pre-" variants

np_acts-logits-general · gemini-2.0-flash

ahead of

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 NUKAT

-0.57

 مشين

-0.57

umos

-0.56

věd

-0.56

 تانيه

-0.55

rawdź

-0.55

 Arro

-0.54

θεια

-0.53

newpage

-0.53

uhr

-0.52

POSITIVE LOGITS

 ahead

1.19

pre

1.04

 preceded

1.01

Pre

1.00

Pre

0.98

 Ahead

0.98

 précé

0.95

pre

0.95

 predeceased

0.93

 pré

0.92

Activations Density 0.060%

details related to mortality and memory

"Ahead" or "pre-" variants

ahead of

No Comments

No Known Activations