INDEX

Explanations

expressions related to programming and function handling

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

()];

-0.59

IVEREF

-0.56

()])

-0.52

++)

-0.52

expandindo

-0.52

پیوند

-0.49

 gênero

-0.48

 >=",

-0.47

GIVEREF

-0.47

льності

-0.47

POSITIVE LOGITS

IntoConstraints

0.69

 utafitiHapana

0.63

CGSize

0.60

 nargin

0.59

 Empieza

0.59

awakeFromNib

0.57

CGRectMake

0.57

ArgsConstructor

0.56

WebVitals

0.56

gonic

0.56

Activations Density 0.314%

expressions related to programming and function handling

No Comments

No Known Activations