INDEX

Explanations

technical terms related to computer architecture and system specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

--]

-0.88

 Plin

-0.83

FRP

-0.76

 conjuncti

-0.72

 Pompe

-0.72

 ligiloj

-0.71

 itſelf

-0.69

 myſelf

-0.69

 sherds

-0.68

 ModelExpression

-0.68

POSITIVE LOGITS

cpu

0.70

CPU

0.68

 processor

0.66

cpu

0.65

processor

0.65

CPU

0.62

دانشنامهٔ

0.60

Processors

0.56

 Processors

0.55

 Processor

0.53

Activations Density 0.234%

technical terms related to computer architecture and system specifications

No Comments

No Known Activations