INDEX

Explanations

instances of attempts or efforts to take action or achieve something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 höchst

-0.59

styleType

-0.56

 Futura

-0.54

 constaté

-0.54

 constater

-0.52

internalType

-0.50

 useAuth

-0.49

 stata

-0.49

 Flores

-0.48

렇

-0.48

POSITIVE LOGITS

 versucht

0.87

 tryna

0.85

 attempts

0.85

 attempt

0.82

ArrowToggle

0.82

SharedDtor

0.81

 tentando

0.78

Attempts

0.77

 versuchen

0.77

 tries

0.77

Activations Density 0.157%

instances of attempts or efforts to take action or achieve something

No Comments

No Known Activations