INDEX

Explanations

references to villages

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 Réponses

-0.75

 scorso

-0.74

 déb

-0.67

abstractmethod

-0.65

://$

-0.60

وذ

-0.60

how

-0.59

 Decken

-0.59

 stiletto

-0.58

msford

-0.58

POSITIVE LOGITS

 Village

1.71

 village

1.70

Village

1.66

 villages

1.63

village

1.60

 VILLAGE

1.52

 Villages

1.44

VILL

1.19

villa

1.19

Vill

1.07

Activations Density 0.008%

references to villages

No Comments

No Known Activations