INDEX

Explanations

programming constructs and structures in code

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

Code snippets or code-related text

np_acts-logits-general · gemini-2.0-flash

code elements and symbols

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.73

 חיצוניים

-0.72

jeka

-0.55

Autoritní

-0.53

]--;

-0.51

 Paglinawan

-0.49

 ")");

-0.49

+};

-0.49

fruta

-0.48

brunn

-0.47

POSITIVE LOGITS

ruptedException

0.59

AutoresizingMask

0.56

 '\\;'

0.53

PickerController

0.52

IBarButtonItem

0.51

myself

0.51

ścic

0.49

KELEY

0.48

webElementGuid

0.48

cokinetic

0.47

Activations Density 0.027%

programming constructs and structures in code

Code snippets or code-related text

code elements and symbols

No Comments

No Known Activations