INDEX

Explanations

specific markers and classifications related to biological identities and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 bier

-0.47

 Leeuwen

-0.43

simpleType

-0.41

 gön

-0.41

 undisclosed

-0.41

arithmic

-0.39

 embed

-0.39

shadowRadius

-0.38

pó

-0.38

ToScroll

-0.38

POSITIVE LOGITS

 disambiguazione

0.71

]")]

0.70

 المعيارى

0.69

TProtocol

0.68

"""

0.65

 distinguishes

0.65

typeorm

0.64

IndentedString

0.64

 distinguishing

0.63

 caractéristique

0.63

Activations Density 0.538%

specific markers and classifications related to biological identities and attributes

No Comments

No Known Activations