INDEX

Explanations

elements related to coding syntax and function definitions

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

C code macros using shift operators

np_acts-logits-general · gemini-2.0-flash

list/code markers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

aarrggbb

-1.28

 Paglinawan

-1.26

Билгалдахарш

-1.20

Personendaten

-1.18

 AssemblyCulture

-1.17

 تضيفلها

-1.17

featureID

-1.14

ьаж

-1.06

GEBURTSDATUM

-1.04

AndEndTag

-1.04

POSITIVE LOGITS

↵

0.48

0.45

0.44

0.43

↵↵↵

0.43

↵↵

0.42

0.41

0.40

ш

0.39

Activations Density 0.633%

elements related to coding syntax and function definitions

C code macros using shift operators

list/code markers

No Comments

No Known Activations