INDEX

Explanations

references to memory and recall of information

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

recollection and memory

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 sitten

-0.45

didSet

-0.35

 appliquer

-0.34

 respetu

-0.31

締切

-0.31

Сылтамалар

-0.29

 ſmall

-0.29

astero

-0.28

 otherwise

-0.28

 förstå

-0.28

POSITIVE LOGITS

rungsseite

0.65

 Paglinawan

0.62

 فريبيس

0.57

 Administrativna

0.57

</tfoot>

0.49

exact

0.49

 resourceCulture

0.49

 Normdatei

0.48

 Exact

0.48

localctx

0.47

Activations Density 0.065%

references to memory and recall of information

recollection and memory

No Comments

No Known Activations