INDEX

Explanations

numerical data, specifically focusing on significant figures or expressions of quantity and measurement

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

apunov

-0.69

featureID

-0.68

 MyClass

-0.67

 bodyParser

-0.65

GEBURTSDATUM

-0.65

bodyParser

-0.62

lawayo

-0.61

 demain

-0.61

بالإنجليزية

-0.60

permitAll

-0.60

POSITIVE LOGITS

 Audiodateien

0.78

__*/

0.78

 reap

0.60

Slu

0.59

enumerate

0.59

Hav

0.58

slu

0.55

@[+][

0.55

риа

0.54

ignons

0.54

Activations Density 0.191%

numerical data, specifically focusing on significant figures or expressions of quantity and measurement

No Comments

No Known Activations