INDEX

Explanations

programming annotations and library references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Attribute

-0.66

 AttributeError

-0.40

RetentionPolicy

-0.37

 Attribute

-0.37

AttributeSet

-0.37

PONENTS

-0.35

MouseAdapter

-0.34

LOOKUP

-0.34

nä

-0.34

fahr

-0.34

POSITIVE LOGITS

tagHelper

6.63

jspx

0.89

CppMethod

0.88

ViewImports

0.84

 ModelExpression

0.83

 surla

0.80

TagHelpers

0.79

featureID

0.78

MessageTagHelper

0.77

 AspNetCore

0.73

Activations Density 0.019%

programming annotations and library references

No Comments

No Known Activations