INDEX

Explanations

references to geographical features and areas in a scientific context

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

TAWA

-0.66

 invokingState

-0.61

الحياه

-0.57

 通販

-0.53

///</

-0.52

CIOS

-0.52

StructEnd

-0.52

Примечания

-0.51

 خارجية

-0.50

 lenker

-0.49

POSITIVE LOGITS

 areas

0.92

 area

0.91

areas

0.83

 vicinity

0.81

 AREAS

0.80

 AREA

0.79

area

0.77

 Areas

0.77

 området

0.71

 Area

0.70

Activations Density 0.494%

references to geographical features and areas in a scientific context

No Comments

No Known Activations