INDEX

Explanations

references to the concept of relevance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 CreateTagHelper

-1.16

ftagPool

-0.77

MigrationBuilder

-0.76

queryInterface

-0.75

 onCreateView

-0.74



-0.74

 "..\..\..\

-0.73

styleType

-0.72

DidLoad

-0.71

orianCalendar

-0.70

POSITIVE LOGITS

 applicable

1.37

 relevant

1.27

applicable

1.11

 Applicable

1.10

relevant

1.05

 APPLICABLE

0.98

 Relevant

0.95

Relevant

0.92

 pertinent

0.92

Applicable

0.92

Activations Density 0.114%

references to the concept of relevance in various contexts

No Comments

No Known Activations