INDEX

Explanations

references to specific geographical locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 '\\;'

-0.67

новништво

-0.65

oredCriteria

-0.63

 мәкал

-0.61

AsUp

-0.60

Microkernel

-0.60

principalTable

-0.59

 Obrador

-0.59

Personensuche

-0.59

webElementXpaths

-0.59

POSITIVE LOGITS

 Springfield

0.53

 Amherst

0.47

 Massachusetts

0.44

 Hampden

0.43

 Westfield

0.43

Springfield

0.43

 Mass

0.40

 Holy

0.38

Eas

0.36

 Hadley

0.35

Activations Density 0.130%

references to specific geographical locations or entities

No Comments

No Known Activations