INDEX

Explanations

instances and variations of the article "a" used in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

quite

-0.63

AddHtmlAttribute

-0.61

 traffico

-0.60

 oldukça

-0.59

 quite

-0.58

 réservé

-0.51

 mycket

-0.51

 destul

-0.51

 molto

-0.51

 popolare

-0.50

POSITIVE LOGITS

rrggbb

0.88

 estekak

0.73

 smile

0.72

GraphicsUnit

0.69

 chance

0.66

 place

0.64

GeneratedMessage

0.62

sense

0.61

lorette

0.61

 AssemblyCompany

0.60

Activations Density 0.376%

instances and variations of the article "a" used in different contexts

No Comments

No Known Activations