INDEX

Explanations

technical terms related to layout and styling 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 @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ActivityResult

-0.67

JNIEnv

-0.56

Välislingid

-0.51

FieldNumber

-0.51

Enllaces

-0.50

Thumb

-0.50

 handle

-0.50

ciales

-0.49

pagna

-0.48

 palmas

-0.48

POSITIVE LOGITS

 font

0.92

font

0.85

 FONT

0.79

 Fonts

0.79

 fonts

0.77

 Font

0.76

 TMPro

0.76

 typography

0.75

 TextStyle

0.73

 ellip

0.73

Activations Density 0.228%

technical terms related to layout and styling in programming contexts

No Comments

No Known Activations