INDEX

Explanations

references to specific geographic locations or service areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

stdbool

-0.36

ppur

-0.34

 addSubview

-0.32

 CreateTagHelper

-0.31

 reç

-0.31

engertian

-0.30

 RECE

-0.30

addSubview

-0.30

 scene

-0.30

 portion

-0.29

POSITIVE LOGITS

 geographically

0.77

 nearest

0.77

 proximity

0.73

 Nearest

0.71

 Proximity

0.70

nearest

0.68

 Distances

0.67

 nearer

0.66

 distances

0.66

 geographical

0.66

Activations Density 0.335%

references to specific geographic locations or service areas

No Comments

No Known Activations