INDEX

Explanations

keywords related to script and coding functions, particularly in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

bootstrapcdn

-1.01

Autoritní

-0.75

 getWidth

-0.71

 kasarigan

-0.69

 serializers

-0.68

)");

-0.67

 autorytatywna

-0.66

rungsseite

-0.66

".

-0.65

HasAnnotation

-0.65

POSITIVE LOGITS

 Mont

0.70

sel

0.68

Mont

0.58

Mom

0.57

Mon

0.56

Greg

0.55

pyplot

0.55

Mon

0.54

SC

0.54

FM

0.53

Activations Density 0.069%

keywords related to script and coding functions, particularly in programming languages

No Comments

No Known Activations