INDEX

Explanations

definitions and grammatical classifications related to verbs and their structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ցված

-0.54

 AssemblyCulture

-0.53

 Informações

-0.49

 posterity

-0.47

ếu

-0.47

ниципа

-0.46

WireFormat

-0.46

devamını

-0.46

 Hered

-0.46

 muualla

-0.46

POSITIVE LOGITS

 ujednoznacz

0.73

Noun

0.67

 noun

0.63

 verbo

0.61

PyExc

0.61

 Familienname

0.59

DataAnnotations

0.59

ToAction

0.57

 Verb

0.57

PRWEB

0.56

Activations Density 0.373%

definitions and grammatical classifications related to verbs and their structures

No Comments

No Known Activations