INDEX

Explanations

programming-related keywords and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

InstrumentedTest

-0.41

 yoksa

-0.33

 незавершена

-0.32

Personendaten

-0.31

 endwhile

-0.31

 Italijani

-0.31

XmlAccessType

-0.31

getDoctrine

-0.29

 <>",

-0.29

<!--[

-0.28

POSITIVE LOGITS

Datuak

0.82

URLException

0.54

ItemBackground

0.53

 Paused

0.52

⪜

0.50

 remittances

0.49

وفاته

0.49

 Batu

0.49

 tolerancia

0.49

openConnection

0.48

Activations Density 0.063%

programming-related keywords and constructs

No Comments

No Known Activations