INDEX

Explanations

references to authorship, parental involvement, and mechanisms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

tagHelperRunner

-0.69

ValueStyle

-0.49

DockStyle

-0.48

featureID

-0.48

 Taktlose

-0.48

AnchorTagHelper

-0.47

참고

-0.47

évaluateur

-0.47

 <<<<<<<<<<<<<<

-0.47

:✨

-0.46

POSITIVE LOGITS

2.39

(-

0.92

(_

0.79

0.78

((

0.75

(\

0.71

0.70

("

0.68

(/

0.68

('

0.66

Activations Density 1.266%

references to authorship, parental involvement, and mechanisms in various contexts

No Comments

No Known Activations