INDEX

Explanations

the repeated use of the particle "が."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 rửa

-0.52

RegistryLite

-0.51

 Brief

-0.51

 waard

-0.50

wój

-0.50

ोजना

-0.49

bilirsiniz

-0.49

dopodob

-0.49

 Fiche

-0.49

ställ

-0.48

POSITIVE LOGITS

が

1.42

가

1.17

が

0.91

が大

0.81

いが

0.80

이

0.78

principalColumn

0.77

 useState

0.75

Autoritní

0.72

PMailer

0.72

Activations Density 0.044%

the repeated use of the particle "が."

No Comments

No Known Activations