INDEX

Explanations

initial tokens that signify the beginning of a new section or topic

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hentet

-0.75

'>{

-0.62

 стаття

-0.61

 saites

-0.59

ivably

-0.58

 indisponible

-0.57

>*/

-0.53

…).

-0.51

!("{

-0.51

]-->

-0.51

POSITIVE LOGITS

 myſelf

0.72

Efq

0.68

 Monfieur

0.65

 للاسماء

0.64

 Chriftian

0.62

 Jefus

0.62

 poffe

0.62

\&

0.61

 houſe

0.60

 himſelf

0.60

Activations Density 0.136%

initial tokens that signify the beginning of a new section or topic

No Comments

No Known Activations