INDEX

Explanations

updates or fixes related to software performance and features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

parsedMessage

-0.88

 linkovi

-0.86

 незавершена

-0.83

 كومونز

-0.83

RectangleBorder

-0.80

DebuggerNonUser

-0.75

createServer

-0.72

expandindo

-0.72

openzeppelin

-0.71

 Wicidata

-0.68

POSITIVE LOGITS

 incorrectly

0.64

 erroneously

0.62

 incorrect

0.61

도록

0.58

 clearer

0.54

 wrongly

0.52

consistent

0.51

 inconsistent

0.50

 penance

0.50

 internally

0.50

Activations Density 0.256%

updates or fixes related to software performance and features

No Comments

No Known Activations

updates or fixes related to software performance and features

No Comments

No Known Activations