INDEX

Explanations

rankings and placements in competitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

={({

-0.62

Viitteet

-0.56

pascal

-0.54

Odkazy

-0.54

timent

-0.54

enumi

-0.49

MathML

-0.49

irited

-0.48

 pascal

-0.48

PMailer

-0.48

POSITIVE LOGITS

<bos>

0.66

 ikinci

0.61

 échou

0.59

 alcuna

0.53

 complètes

0.52

avimas

0.51

entile

0.50

 sonre

0.50

 ranked

0.50

 nessuna

0.50

Activations Density 0.104%

rankings and placements in competitions

No Comments

No Known Activations