INDEX

Explanations

patterns related to character types and valid identifier formats 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

farwyddwr

-0.73

ditor

-0.64

 Préférences

-0.63

 esternos

-0.63

 odkazy

-0.62

IsContent

-0.62

/−

-0.62

albums

-0.59

 صوتيه

-0.59

\"></

-0.59

POSITIVE LOGITS

 numbers

0.92

 digits

0.91

 numeric

0.87

 数字

0.82

isdigit

0.81

digits

0.78

数字

0.76

 numerals

0.75

 numeral

0.75

strconv

0.75

Activations Density 0.280%

patterns related to character types and valid identifier formats in programming

No Comments

No Known Activations