INDEX

Explanations

programming-related terms and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

+#+#

-0.66

)");

-0.64

AccessorTable

-0.64

 betweenstory

-0.64

EDEFAULT

-0.63

 referenties

-0.62

 jura

-0.60

printStackTrace

-0.59

tonode

-0.57

ContextHolder

-0.55

POSITIVE LOGITS

 normalidad

0.56

 Sequelize

0.53

 skydd

0.52

 fallait

0.52

 étrangères

0.50

 ordinaires

0.49

 réguli

0.49

maco

0.47

 rempli

0.47

 Lott

0.47

Activations Density 0.659%

programming-related terms and syntax elements

No Comments

No Known Activations