INDEX

Explanations

code-related terms involving property manipulation and node handling in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Umgang

-0.40

 Mulher

-0.40

 ferner

-0.37

 doInBackground

-0.35

Autoritní

-0.35

esk

-0.34

ioutil

-0.34

ulturally

-0.34

 createSprite

-0.34

foglio

-0.33

POSITIVE LOGITS

 NSCoder

0.56

velocityY

0.51

webElement

0.50

seamnă

0.50

 Infórmanos

0.48

principalColumn

0.48

 Chwiliwch

0.44

 mergeFrom

0.43

 faudrait

0.43

 <>",

0.40

Activations Density 0.475%

code-related terms involving property manipulation and node handling in programming

No Comments

No Known Activations