INDEX

Explanations

elements of code or programming concepts, particularly focusing on specific syntactical elements and structures

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

numbers and codes

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SharedCtor

-0.46

dafx

-0.43

AccessorTable

-0.42

GEBURTSDATUM

-0.41

 referenties

-0.39

 Վերցված

-0.38

awtextra

-0.36

IndentedString

-0.32

 kautta

-0.31

แล้ว

-0.31

POSITIVE LOGITS

Tembelea

0.55

ABUL

0.54

ngthen

0.54

CodeAttribute

0.53

FieldNumber

0.52

Bollywood

0.51

sembles

0.50

 Caesars

0.49

ounid

0.49

ousands

0.49

Activations Density 0.003%

elements of code or programming concepts, particularly focusing on specific syntactical elements and structures

numbers and codes

No Comments

No Known Activations