INDEX

Explanations

concepts and terms related to changes, comparisons, and different properties 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 @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Provenance

-0.50

 stalo

-0.50

壤

-0.49

SOUNDBITE

-0.48

سكرية

-0.47

envolvimento

-0.47

didReceive

-0.46

getLogger

-0.46

boots

-0.44

xically

-0.44

POSITIVE LOGITS

 aspects

0.96

 things

0.92

 features

0.89

 للاسماء

0.83

 nuances

0.83

AutoresizingMask

0.79

PerformLayout

0.78

 tasks

0.75

 amenities

0.75

 saker

0.74

Activations Density 1.049%

concepts and terms related to changes, comparisons, and different properties in various contexts

No Comments

No Known Activations