INDEX

Explanations

the repetition of the particle "を" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Efq

-0.70

 itſelf

-0.68

 bigli

-0.65

 onOptions

-0.63

 Verhält

-0.63

 stiefel

-0.62

 Karls

-0.62

 MAIS

-0.61

 sandero

-0.61

 okaza

-0.61

POSITIVE LOGITS

ceğini

0.78

devamını

0.78

 को

0.77

://"

0.77

ığını

0.74

mybatisplus

0.72

ısını

0.71

かを

0.71

 را

0.70

いを

0.69

Activations Density 0.060%

the repetition of the particle "を" in various contexts

No Comments

No Known Activations