INDEX

Explanations

elements related to numerical data or measurement within a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

脚注の使い方

-0.71

 continúas

-0.70

.*")]

-0.69

 متعلقه

-0.65

/*

-0.64



-0.62

ValueStyle

-0.62

 дописавши

-0.60

abestanden

-0.60

UnknownFields

-0.59

POSITIVE LOGITS

characteristics

0.51

 behalf

0.48

properties

0.46

LookAnd

0.45

ositol

0.44

 characteristics

0.44

 của

0.43

attributes

0.43

Characteristics

0.43

PickerController

0.43

Activations Density 0.944%

elements related to numerical data or measurement within a context

No Comments

No Known Activations