INDEX

Explanations

references to classes and objects within programming or software components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

LookAnd

-0.90

 للمعارف

-0.89

webElementXpaths

-0.88

UnusedPrivate

-0.86

SharedDtor

-0.86

 transfieras

-0.85

onAttach

-0.82

ftagPool

-0.81

ThroughAttribute

-0.80

AsUp

-0.79

POSITIVE LOGITS

Portály

0.47

UDC

0.44

pecies

0.44

érons

0.44

ství

0.43

orologio

0.42

 quadros

0.41

одно

0.40

RCS

0.40

 LUMP

0.39

Activations Density 0.033%

references to classes and objects within programming or software components

No Comments

No Known Activations