INDEX

Explanations

programming-related elements and syntax in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 snippetHide

-0.74

 WebDriverWait

-0.65

awtextra

-0.62

MemoryWarning

-0.59

 IBOutlet

-0.59

HtmlAttribute

-0.58

 TextEditing

-0.58

edicated

-0.53

 mathematicians

-0.51

 géant

-0.50

POSITIVE LOGITS

Enumerated

0.80

XmlEnum

0.63

 choose

0.61

Enum

0.60

choose

0.59

 enum

0.59

 choosing

0.58

 selecting

0.57

Choosing

0.57

 decide

0.56

Activations Density 0.736%

programming-related elements and syntax in code

No Comments

No Known Activations