INDEX

Explanations

references to nested structures and attributes 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

thly

-0.56

 transférez

-0.55

 iprot

-0.54

ihnachts

-0.54

PostConstruct

-0.53

 gynhyrchwyd

-0.52

Cyril

-0.52

setupUi

-0.52

gimento

-0.49

adze

-0.48

POSITIVE LOGITS

 Caste

0.65

tonode

0.63

солю

0.63

 scalars

0.61

 Cohort

0.60

 isbn

0.59

 buzzing

0.59

 tray

0.57

 aphid

0.57

 chère

0.56

Activations Density 2.651%

references to nested structures and attributes in programming

No Comments

No Known Activations