INDEX

Explanations

specific phrases or constructs related to fictional combat units or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

EDEFAULT

-0.53

ThroughAttribute

-0.53

 supplémentaires

-0.47

 mijne

-0.47

vertx

-0.46

'{@

-0.46

Bioaccumulative

-0.46

jsoup

-0.45

ionView

-0.44

árny

-0.43

POSITIVE LOGITS

WireFormatLite

0.85

OGND

0.68

 disambiguazione

0.66

homonymie

0.65

 kasarigan

0.65

ArrowToggle

0.64

 censiti

0.63

CppMethod

0.59

 ComVisible

0.57

isNameExpr

0.56

Activations Density 0.204%

specific phrases or constructs related to fictional combat units or characters

No Comments

No Known Activations