INDEX

Explanations

references to mathematical or statistical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

apimachinery

-0.66

তথ্যসূত্র

-0.65

hematical

-0.63

'&

-0.61

\{\\

-0.59

 tslint

-0.58

ITHUB

-0.55

Lähteet

-0.55

sprogramm

-0.55

Chú

-0.55

POSITIVE LOGITS

RegistryLite

0.59

extAlignment

0.58

randomUUID

0.53

Recognizer

0.53

CloseOperation

0.52

building

0.50

 Determined

0.50

locals

0.49

GEBURTSDATUM

0.48

Employee

0.47

Activations Density 0.172%

references to mathematical or statistical models

No Comments

No Known Activations