INDEX

Explanations

elements related to technical terminology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.69

hésite

-0.64

RegressionTest

-0.64

 BoxDecoration

-0.60

+:+

-0.59

 doubtnut

-0.58

 PopupWindow

-0.57

NameInMap

-0.57

pintura

-0.56

Geplaatst

-0.55

POSITIVE LOGITS

aka

0.72

aka

0.67

AKA

0.65

bootstrapcdn

0.64

 tức

0.61

AKA

0.61

也就是

0.60

setopt

0.59

 capital

0.59

と呼ばれる

0.57

Activations Density 0.622%

elements related to technical terminology

No Comments

No Known Activations