INDEX

Explanations

keywords and constructs related to programming functions and operations

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

Code related parameters/arguments

np_acts-logits-general · gemini-2.0-flash

code structure and keywords

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

ling

-0.42

ht

-0.41

ah

-0.40

aban

-0.39

or

-0.39

 dead

-0.38

ković

-0.38

JdbcTemplate

-0.37

otts

-0.37

աստ

-0.36

POSITIVE LOGITS

 للاسماء

0.90

لينكات

0.80

 صوتيه

0.78

Personendaten

0.74

 }}"></

0.73

الإنجليزية

0.72

TryParse

0.72

 uParam

0.71

 GenerationType

0.70

IsContent

0.69

Activations Density 0.214%

keywords and constructs related to programming functions and operations

Code related parameters/arguments

code structure and keywords

No Comments

No Known Activations