INDEX

Explanations

terms related to search functionality and website navigation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Билгалдахарш

-1.10

ViewFeatures

-1.08

aarrggbb

-1.07

ImageContext

-1.03

Tikang

-1.00

 дописавши

-0.98

SharedCtor

-0.97

 Италијани

-0.97

ContentAsync

-0.96

 utafitiHapana

-0.95

POSITIVE LOGITS

 indépendante

0.53

 disparu

0.46

 indipendente

0.46

 sèche

0.43

的

0.40

 viejos

0.39

 της

0.39

 secas

0.38

 mencionado

0.38

 vecchio

0.38

Activations Density 0.286%

terms related to search functionality and website navigation

No Comments

No Known Activations