INDEX

Explanations

elements related to code iterations and loops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

partimento

-0.62

awaiter

-0.59

ResponseBody

-0.58

 ModelRenderer

-0.54

 الدولى

-0.51

 extiende

-0.48

XmlAttribute

-0.48

 participé

-0.48

Espèce

-0.47

RTSC

-0.47

POSITIVE LOGITS

 ***!

0.71

 BoxDecoration

0.60

 autorytatywna

0.59

postIndex

0.58

новниш

0.56

 positions

0.52

0.51

adpleegd

0.51

 position

0.50

Revenir

0.50

Activations Density 0.063%

elements related to code iterations and loops

No Comments

No Known Activations