INDEX

Explanations

programming-related keywords and syntax structures

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

Code or symbols mixed in text

np_acts-logits-general · gemini-2.0-flash

mathematical expressions and code elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptonshire

-0.65

 AssemblyTitle

-0.62

 StatefulWidget

-0.62

 désolés

-0.60

EndProject

-0.59

 utafitiHapana

-0.57

 Krim

-0.56

########.

-0.56

DataAnnotations

-0.55

voi

-0.53

POSITIVE LOGITS

OrBuilder

0.82

bitField

0.80

 Zeke

0.58

 java

0.56

FieldBuilder

0.52

java

0.51

 thatched

0.51

الحياه

0.48

IsMutable

0.48

 createSlice

0.47

Activations Density 0.067%

programming-related keywords and syntax structures

Code or symbols mixed in text

mathematical expressions and code elements

No Comments

No Known Activations