INDEX

Explanations

references to specific locations or contexts where events or actions occur

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

Preceding "general" or related to research/work

np_acts-logits-general · gemini-2.0-flash

in general

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 riuscito

-0.63

 ClassNotFound

-0.55

sat

-0.51

 notare

-0.49

]")]

-0.49

providedIn

-0.48

 left

-0.46

 riusc

-0.46

ClassNotFound

-0.46

 BadRequest

-0.46

POSITIVE LOGITS

 general

0.81

 workplaces

0.65

general

0.65

GraphicsUnit

0.65

 ways

0.65

 EconPapers

0.64

 itſelf

0.63

\{\\

0.62

eneral

0.61

 contextos

0.60

Activations Density 0.429%

references to specific locations or contexts where events or actions occur

Preceding "general" or related to research/work

in general

No Comments

No Known Activations