INDEX

Explanations

code constructs and class definitions in programming

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

 snippetHide

-0.77

efes

-0.56

 useAppContext

-0.54

 ویکی

-0.51

 CreateTagHelper

-0.50

gil

-0.49

getContentPane

-0.48

 TextAppearance

-0.48

wachs

-0.48

∬

-0.47

POSITIVE LOGITS

 purpoſe

0.68

 myſelf

0.62

 auffi

0.61

 ainfi

0.60

 juſ

0.60

EndProject

0.58

 pleaſure

0.58

routeProvider

0.57

 Reſ

0.57

 ſever

0.56

Activations Density 0.069%

code constructs and class definitions in programming

No Comments

No Known Activations