INDEX

Explanations

fragments of code related to annotations and configuration settings 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

kloped

-0.56

Kost

-0.54

 OMIT

-0.51

 ſtand

-0.51

Vidite

-0.50

IsMutable

-0.50

ấn

-0.50

pezi

-0.50

 stry

-0.50

 Playback

-0.49

POSITIVE LOGITS

 kasarigan

0.62

VersionUID

0.62

MemoryWarning

0.60

CGRectMake

0.58

 MonoBehaviour

0.58

SuspendLayout

0.57

 CreateTagHelper

0.57

cshtml

0.56

 IndexPath

0.55

Activations Density 0.039%

fragments of code related to annotations and configuration settings in programming

No Comments

No Known Activations