INDEX

Explanations

instances of variable or function declarations related to handlers and system outputs in code

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

Code snippets/programming language

np_acts-logits-general · gemini-2.0-flash

code keywords and symbols

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

 cdti

-0.66

alnız

-0.66

 Monfieur

-0.66

PreferredItem

-0.64

 hunne

-0.61

 Cæsar

-0.60

WindowConstants

-0.59

 carats

-0.59

glTranslatef

-0.59

oredCriteria

-0.57

POSITIVE LOGITS

tagHelperRunner

0.75

 تضيفلها

0.69

ⓧ

0.63

wikidata

0.59

DIPSETTING

0.55

υσ

0.51

utin

0.51

󠁿

0.51

Искәрмәләр

0.49

 muito

0.47

Activations Density 0.129%

instances of variable or function declarations related to handlers and system outputs in code

Code snippets/programming language

code keywords and symbols

No Comments

No Known Activations