INDEX

Explanations

terms related to nodes in a computing or programming context

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

"node" and related programming terms

np_acts-logits-general · gemini-2.0-flash

node.js context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

plash

-0.60

 androidx

-0.55

?>">

-0.54

*/),

-0.54

--)

-0.54

WebVitals

-0.53

}},\

-0.53

Sve

-0.53

`]

-0.53

 relativity

-0.52

POSITIVE LOGITS

 nodes

1.49

 Nodes

1.39

 node

1.37

 Node

1.28

nodes

1.17

 NODE

1.16

 getNode

1.11

NODE

1.08

getNode

1.05

Node

1.04

Activations Density 0.120%

terms related to nodes in a computing or programming context

"node" and related programming terms

node.js context

No Comments

No Known Activations