INDEX

Explanations

segments related to scientific acknowledgments and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

DockStyle

-0.63

 }}"></

-0.56

kloped

-0.55

%)$

-0.55

 كومونز

-0.54

 FormData

-0.54

ectady

-0.54

astă

-0.53

MTT

-0.52

Enllaces

-0.52

POSITIVE LOGITS

DebuggerNonUser

0.72

NameInMap

0.65

 udaler

0.59

 propOrder

0.58

enterOuterAlt

0.56

GeneratedMessage

0.52

 kasarigan

0.52

SuccessListener

0.48

Архівовано

0.48

Kariera

0.46

Activations Density 0.888%

segments related to scientific acknowledgments and publications

No Comments

No Known Activations