INDEX

Explanations

prepositions indicating a relational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 Monfieur

-0.97

ſelves

-0.90

 Jefus

-0.87

 Cæsar

-0.85

 houſe

-0.84

 Houſe

-0.84

Efq

-0.84

ſelf

-0.83

 Reſ

-0.82

ScopeManager

-0.82

POSITIVE LOGITS

 most

0.58

0.57

toEqual

0.53

مصادر

0.52

 vět

0.50

 кӀ

0.49

có

0.49

 even

0.48

حياته

0.48

 notable

0.48

Activations Density 0.059%

prepositions indicating a relational context

No Comments

No Known Activations

prepositions indicating a relational context

No Comments

No Known Activations