INDEX

Explanations

proper nouns, specifically names of locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

脚注の使い方

-0.75

StructEnd

-0.64

 betweenstory

-0.63

AutoField

-0.62

HasForeignKey

-0.60

PerformLayout

-0.59

 Wiktionnaire

-0.57

 OFDb

-0.56

liceerd

-0.54

MemoryWarning

-0.52

POSITIVE LOGITS

VILLE

0.64

DC

0.64

DC

0.64

Mam

0.63

Atlanta

0.60

 Georgia

0.60

ville

0.60

Mam

0.60

 Atlanta

0.59

Activations Density 0.345%

proper nouns, specifically names of locations

No Comments

No Known Activations