INDEX

Explanations

references to acknowledgments and gratitude in research papers

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

acknowledgements and contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 celebrid

-0.38

 experto

-0.38

 suele

-0.37

早速

-0.37

 suscripción

-0.36

írus

-0.35

 atractivo

-0.35

 inmediato

-0.35

 popularidad

-0.35

InitStruct

-0.34

POSITIVE LOGITS

 research

0.64

AndEndTag

0.60

 graduate

0.60

 Graduate

0.58

 ErrIntOverflow

0.58

पया

0.58

Graduate

0.57

transQ

0.57

research

0.56

EndInit

0.54

Activations Density 0.012%

references to acknowledgments and gratitude in research papers

acknowledgements and contributions

No Comments

No Known Activations