INDEX

Explanations

technical terms related to physical components and their assembly

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

AndEndTag

-0.98

BeginInit

-0.80

 متعلقه

-0.75

 doInBackground

-0.71

mybatisplus

-0.70

Personendaten

-0.69

SequentialGroup

-0.69

 Signalez

-0.67

 ModelExpression

-0.67

 hedges

-0.65

POSITIVE LOGITS

 aftermarket

0.81

 install

0.79

 installed

0.71

 mounting

0.69

 rear

0.68

 removable

0.65

 factory

0.65

 replacement

0.64

 installing

0.64

 remplacement

0.63

Activations Density 0.699%

technical terms related to physical components and their assembly

No Comments

No Known Activations