INDEX

Explanations

terms related to geographical locations and localization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FAP

-0.83

IsMutable

-0.79

HEP

-0.77

StructEnd

-0.75

phrine

-0.75

]^{-

-0.73

_('

-0.72

 diarios

-0.72

 ISNI

-0.70

MigrationBuilder

-0.67

POSITIVE LOGITS

 location

1.61

 Location

1.48

 Locations

1.46

 LOCATION

1.42

LLocation

1.42

 locations

1.42

locations

1.35

Location

1.35

Loc

1.35

Locations

1.32

Activations Density 0.042%

terms related to geographical locations and localization

No Comments

No Known Activations