INDEX

Explanations

technical terms related to mobile station capabilities and messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

by

-0.51

hem

-0.47

No

-0.46

no

-0.45

out

-0.44

sy

-0.43

empio

-0.41

 löytyy

-0.41

We

-0.41

we

-0.41

POSITIVE LOGITS

GEBURTSDATUM

1.30

 فريبيس

0.98

queryInterface

0.87

rungsseite

0.86

featureID

0.84

 initComponents

0.83

 resourceCulture

0.82

 ComVisible

0.80

PerformLayout

0.80

LookAnd

0.79

Activations Density 1.008%

technical terms related to mobile station capabilities and messages

No Comments

No Known Activations