INDEX

Explanations

coding concepts related to graphics and drawing functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Waray

-0.73

 disambiguazione

-0.69

lampen

-0.59

mögens

-0.54

 Tapatalk

-0.54

RUnlock

-0.52

wissenschaft

-0.52

 rosto

-0.52

setCharacter

-0.52

 ✭✭

-0.51

POSITIVE LOGITS

 stroke

0.76

 strokes

0.74

 fill

0.69

stroke

0.66

 Stroke

0.64

 Fill

0.63

 Path

0.62

Path

0.60

path

0.57

strokes

0.57

Activations Density 0.249%

coding concepts related to graphics and drawing functions

No Comments

No Known Activations