INDEX

Explanations

topics related to health and wellness

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

Followed by verbs/actions

np_acts-logits-general · gemini-2.0-flash

technical terms and concepts

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

älj

-0.57

oredCriteria

-0.56

 scolaires

-0.56

istoitu

-0.55

riedenheit

-0.55

 similaire

-0.53

yelitis

-0.52

ersham

-0.51

 pharmaceuticals

-0.51

oulli

-0.51

POSITIVE LOGITS

WireFormatLite

0.61

 resourceCulture

0.59

DebuggerNonUser

0.54

 particular

0.53

 maravilh

0.53

AddressBook

0.52

 ComVisible

0.52

particular

0.51

 createState

0.51

AlterField

0.49

Activations Density 0.669%

topics related to health and wellness

Followed by verbs/actions

technical terms and concepts

No Comments

No Known Activations