INDEX

Explanations

mathematical expressions and structures related to arrays and their properties

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

"array" or similar

np_acts-logits-general · gemini-2.0-flash

array and arrays

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

wik

-0.54

 bitter

-0.49

gins

-0.48

bitter

-0.48

ignite

-0.47

addWidget

-0.47

 mouseClicked

-0.47

 Adam

-0.46

 Thorn

-0.46

Thorn

-0.45

POSITIVE LOGITS

 array

1.91

array

1.80

 arrays

1.69

 Array

1.65

Array

1.58

 ARRAY

1.56

ARRAY

1.51

 Arrays

1.48

arrays

1.39

 arrayed

1.36

Activations Density 0.174%

mathematical expressions and structures related to arrays and their properties

"array" or similar

array and arrays

No Comments

No Known Activations