INDEX

Explanations

references to programming constructs, specifically in relation to JavaScript and PHP coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

lüğ

-0.63

 œil

-0.59

 jouet

-0.56

 tuyau

-0.52

 boîtier

-0.51

 oeil

-0.50

før

-0.50

 vêtement

-0.48

 pistolet

-0.48

 idéia

-0.47

POSITIVE LOGITS

 queſta

0.73



0.66

$_"

0.62

Efq

0.62

 bluzka

0.62

 Monfieur

0.61

 للاسماء

0.60

 abstrato

0.59

 tirage

0.59

 Geſ

0.58

Activations Density 0.171%

references to programming constructs, specifically in relation to JavaScript and PHP coding

No Comments

No Known Activations