INDEX

Explanations

terms related to directed graphs and their structures

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

"Direction" or "directed" preceding another word

np_acts-logits-general · gemini-2.0-flash

directed acyclic graphs

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

MessageTagHelper

-0.66

})*/

-0.59

MessageOf

-0.59

ngdoc

-0.58

 CommonModule

-0.57

 мәкалә

-0.56

 convertView

-0.56

ikkert

-0.55

wts

-0.55

وه

-0.54

POSITIVE LOGITS

ality

0.85

 artistique

0.70

Eſ

0.63

 AssemblyCulture

0.62

 sportif

0.61

alty

0.61

 Toward

0.60

 Canary

0.58

 Towards

0.57

 själ

0.57

Activations Density 0.126%

terms related to directed graphs and their structures

"Direction" or "directed" preceding another word

directed acyclic graphs

No Comments

No Known Activations