INDEX

Explanations

elements related to arrays and their operations in programming contexts

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

Words/tokens preceding "array" or "arrays"

np_acts-logits-general · gemini-2.0-flash

action arrays or antenna arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

TagMode

-0.50

eds

-0.47

 Réponses

-0.45

Fid

-0.45

AddTagHelper

-0.45

 &___

-0.44

IsContent

-0.42

Adam

-0.42

parsedMessage

-0.42

POSITIVE LOGITS

 array

3.30

array

3.02

 Array

2.80

Array

2.63

 arrays

2.40

 ARRAY

2.17

ARRAY

2.14

 Arrays

2.03

数组

1.89

arrays

1.82

Activations Density 0.171%

elements related to arrays and their operations in programming contexts

Words/tokens preceding "array" or "arrays"

action arrays or antenna arrays

No Comments

No Known Activations