INDEX

Explanations

references to various programming constructs and elements in code, particularly focusing on data structures and methods related to class attributes and file handling

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

Code, state, or proxy-related words

np_acts-logits-general · gemini-2.0-flash

programming code keywords

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

OGND

-0.89

fjspx

-0.74

Rohy

-0.51

Gweler

-0.49

 estekak

-0.48

rode

-0.47

Хьажоргаш

-0.47

 Normdatei

-0.47

 resourceCulture

-0.47

 ſte

-0.46

POSITIVE LOGITS

 pieles

0.48

 inmueble

0.46

 creativos

0.44

 createState

0.43

 cristales

0.43

parsedMessage

0.43

 ganchillo

0.42

 tersebut

0.42

 antemano

0.42

 mármol

0.41

Activations Density 0.351%

references to various programming constructs and elements in code, particularly focusing on data structures and methods related to class attributes and file handling

Code, state, or proxy-related words

programming code keywords

No Comments

No Known Activations