INDEX

Explanations

terms related to automated processes or functionalities

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

beginning with "Auto"

np_acts-logits-general · gemini-2.0-flash

words starting with "auto"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

MessageInfo

-0.60

 Alpes

-0.57

 }}"></

-0.56

 cardiaque

-0.53

 "..\..\..\

-0.53

Jeografia

-0.51

celine

-0.49

)]:

-0.49

MergeFrom

-0.48

 commerciali

-0.47

POSITIVE LOGITS

 AUTO

0.84

 Auto

0.80

 Autos

0.79

 فريبيس

0.78

setAuto

0.75

 ricks

0.74

Autos

0.70

Auto

0.68

 defaultstate

0.68

bahn

0.67

Activations Density 0.083%

terms related to automated processes or functionalities

beginning with "Auto"

words starting with "auto"

No Comments

No Known Activations