INDEX

Explanations

phrases indicating components or aspects of a larger entity

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

 nullptr

-0.64

Kore

-0.61

Tcp

-0.59

Iq

-0.59

gac

-0.59

vmware

-0.58

 Decatur

-0.58

genstein

-0.57

ewoo

-0.56

IService

-0.56

POSITIVE LOGITS

 integrante

0.96

 ramach

0.92

 Bestandteil

0.88

částí

0.86

 rámci

0.85

 ضمن

0.84

 integrantes

0.81

Portail

0.81

 onderdeel

0.77

Erreferentziak

0.73

Activations Density 0.162%

phrases indicating components or aspects of a larger entity

No Comments

No Known Activations

phrases indicating components or aspects of a larger entity

No Comments

No Known Activations