INDEX

Explanations

references to images, files, or visual elements in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Wicidata

-0.75

曖昧さ回避

-0.74

SBATCH

-0.74

 незавершена

-0.68

NewUrlParser

-0.67

 utafitiHapana

-0.67

 ब्रेकडाउन

-0.67

thrower

-0.66

strual

-0.66

Архівовано

-0.66

POSITIVE LOGITS

↵↵

0.67

mtable

0.50

yti

0.50

 konuş

0.49

↵

0.46

нець

0.46

 arada

0.45

 chimiques

0.45

$\

0.45

↵↵↵

0.44

Activations Density 0.085%

references to images, files, or visual elements in the document

No Comments

No Known Activations