INDEX

Explanations

terms related to data or programming with a focus on user interface components and shader programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rungsseite

-0.71

Географи

-0.58

DockStyle

-0.55

egy

-0.54

 encoded

-0.52

mektedir

-0.52

 surcharge

-0.52

 calendriers

-0.52

Приятного

-0.51

 samfun

-0.51

POSITIVE LOGITS

 Cape

0.81

Personendaten

0.79

OGND

0.75

Cape

0.74

XtraGrid

0.73

 bench

0.68

 AttributeSet

0.68

 Mate

0.68

 dignity

0.66

 CAPE

0.65

Activations Density 0.806%

terms related to data or programming with a focus on user interface components and shader programming

No Comments

No Known Activations