INDEX

Explanations

terms related to data structures and their attributes in programming contexts

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

Code-related lists or arrays

np_acts-logits-general · gemini-2.0-flash

list or array contents and structure

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

enumi

-0.80

Хьажоргаш

-0.62

thâu

-0.52

enumii

-0.49

yet

-0.48

because

-0.48

valry

-0.47

기도

-0.47

Portale

-0.47

KommentareTeilen

-0.47

POSITIVE LOGITS

 representing

1.00

 containing

0.95

 whose

0.91

 représentant

0.89

 describing

0.88

 consisting

0.88

 specifying

0.80

 holding

0.78

 represented

0.77

 contenant

0.74

Activations Density 0.488%

terms related to data structures and their attributes in programming contexts

Code-related lists or arrays

list or array contents and structure

No Comments

No Known Activations