INDEX

Explanations

references to actions related to data management and interactions

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

Follows a verb in passive voice

np_acts-logits-general · gemini-2.0-flash

infected with, added to, data for

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

AccessorTable

-0.47

gent

-0.45

 poly

-0.45

 Wicidata

-0.45

mal

-0.44

-0.43

Portály

-0.43

-0.41

실

-0.40

itzer

-0.39

POSITIVE LOGITS

 withal

1.01

脚注の使い方

0.70

NewUrlParser

0.67

 متعلقه

0.65

WebServlet

0.65

AddTagHelper

0.63

 uintptr

0.62

thenReturn

0.61

rouvez

0.60

SequentialGroup

0.58

Activations Density 0.305%

references to actions related to data management and interactions

Follows a verb in passive voice

infected with, added to, data for

No Comments

No Known Activations