INDEX

Explanations

references to research studies and collaborative projects

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

"as part of"

np_acts-logits-general · gemini-2.0-flash

as part of

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 propOrder

-0.93

mybatisplus

-0.77

}-*/;

-0.76



-0.74

 fieldNum

-0.71

 SwitchCompat

-0.70

EndInit

-0.70

RetentionPolicy

-0.69

 pinulongan

-0.69

QMetaType

-0.69

POSITIVE LOGITS

 part

1.60

part

1.22

 parte

1.15

 במס

1.10

的一部分

1.05

 onderdeel

1.05

 כח

1.01

 ramach

1.00

 bagian

0.95

 рамках

0.94

Activations Density 0.347%

references to research studies and collaborative projects

"as part of"

as part of

No Comments

No Known Activations