INDEX

Explanations

references to null values or non-existent data within various contexts

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

Code snippets containing variables initialized to zero or NULL followed by semicolons

np_acts-logits-general · gemini-2.0-flash

code statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 архивлан

-0.68

Portail

-0.66

__(/*!

-0.65

__':

-0.64

 Dicapai

-0.63

postValue

-0.63

)"),

-0.62

PhysRev

-0.60

 referenties

-0.59

*/

-0.59

POSITIVE LOGITS

ArgsConstructor

0.62

piram

0.59

олові

0.54

 obligé

0.50

 attiva

0.49

databind

0.48

BagConstraints

0.47

 Socialista

0.47

ArgumentParser

0.47

Activations Density 0.095%

references to null values or non-existent data within various contexts

Code snippets containing variables initialized to zero or NULL followed by semicolons

code statements

No Comments

No Known Activations