INDEX

Explanations

posts expressing confusion or seeking clarification

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

QtWidgets

-0.50

 alle

-0.47

Attention

-0.44

Général

-0.42

createCanvas

-0.42

phus

-0.41

carta

-0.40

alih

-0.40

 المش

-0.39

savefig

-0.39

POSITIVE LOGITS

новниш

0.87

Efq

0.82

BeginContext

0.79

 myſelf

0.79

 Theſe

0.76

COUVER

0.75

InjectAttribute

0.74

 posting

0.73

EndInit

0.73

 ویکی‌پدیا

0.73

Activations Density 0.356%

posts expressing confusion or seeking clarification

No Comments

No Known Activations