INDEX

Explanations

key phrases that indicate essential components or aspects of subjects discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Roskov

-0.76

 MainAxisSize

-0.61

 StatefulWidget

-0.60

 ModelExpression

-0.58

SharedCtor

-0.58

withIdentifier

-0.58

verwijspagina

-0.57

 resourceCulture

-0.56

setVerticalGroup

-0.55

 viewDidLoad

-0.54

POSITIVE LOGITS

 part

4.27

part

3.56

Part

3.07

 parte

3.00

 Part

2.81

 parts

2.63

 PART

2.60

 часть

2.45

 Teil

2.44

 bagian

2.28

Activations Density 1.155%

key phrases that indicate essential components or aspects of subjects discussed

No Comments

No Known Activations