INDEX

Explanations

references to programming structures and data types

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

Symbols and special characters

np_acts-logits-general · gemini-2.0-flash

code constructs and foreign words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

󠁴

-0.56

:✨

-0.49

 OFDb

-0.49

DO

-0.47

Hochspringen

-0.46

፩

-0.46

 transfieras

-0.46

oredCriteria

-0.45

ьа

-0.45

IPT

-0.45

POSITIVE LOGITS

tagHelperRunner

0.49

andExpect

0.45

bitField

0.43

 contigo

0.41

 Erscheinung

0.41

 registrazione

0.40

 powiedzieć

0.40

 adentro

0.38

 llegamos

0.37

postmedia

0.36

Activations Density 0.402%

references to programming structures and data types

Symbols and special characters

code constructs and foreign words

No Comments

No Known Activations