INDEX

Explanations

segments of code or comments often associated with documentation and function descriptions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ModelExpression

-0.75

Previews

-0.65

SOUNDBITE

-0.56

Personendaten

-0.55

Aiheesta

-0.54

JspWriter

-0.53

 jspb

-0.53

Vidite

-0.52

Бележки

-0.52

رشف

-0.51

POSITIVE LOGITS

================

0.67

----------------

0.67

------

0.58

————————

0.57

☸

0.55

-------------

0.55

 getContent

0.54

****************

0.53

Lebens

0.53

ssysteme

0.53

Activations Density 0.198%

segments of code or comments often associated with documentation and function descriptions in programming contexts

No Comments

No Known Activations