INDEX

Explanations

numeric data and structured information related to signal processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 itſelf

-0.83

RegressionTest

-0.80

Efq

-0.78

 الرياضيه

-0.77

EDEFAULT

-0.76

 ſche

-0.73

didSet

-0.71

 дописавши

-0.71

 myſelf

-0.69

ImageContext

-0.68

POSITIVE LOGITS

Kaw

0.57

Mc

0.56

ran

0.54

ceral

0.51

we

0.48

ukum

0.48

 solidari

0.48

Kaw

0.47

исленность

0.47

 jPanel

0.47

Activations Density 1.090%

numeric data and structured information related to signal processing

No Comments

No Known Activations