INDEX

Explanations

layout and alignment properties in design and implementation contexts

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

Datuak

-0.76

IMPORTED

-0.70

 Roskov

-0.68

 tartalomajánló

-0.66

Sucesor

-0.66

Hochspringen

-0.65

Portail

-0.65

RegistryLite

-0.64

पया

-0.64

 ویکی‌پدیا

-0.64

POSITIVE LOGITS

center

0.76

 center

0.66

CENTER

0.63

centerTitle

0.61

 centre

0.60

Center

0.59

 Center

0.59

 CENTER

0.57

centre

0.55

 BoxFit

0.53

Activations Density 0.026%

layout and alignment properties in design and implementation contexts

No Comments

No Known Activations