INDEX

Explanations

elements related to families and relationships

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

 photolibrary

-0.89

__":

-0.85

 Paglinawan

-0.83

__).

-0.79

Pautan

-0.78

AndEndTag

-0.77

*/;

-0.77

(!__

-0.75

цездатний

-0.75

>";

-0.74

POSITIVE LOGITS

 właśnie

0.51

 among

0.44

<em>

0.42

genöss

0.40

en

0.39

 gehö

0.39

 právě

0.39

 mention

0.39

<u>

0.37

Among

0.37

Activations Density 0.535%

elements related to families and relationships

No Comments

No Known Activations