INDEX

Explanations

numbers and statistical values related to medical data

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

Negative numbers and arithmetic operations

np_acts-logits-general · gemini-2.0-flash

numbers and symbols

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

-1.18

 fifteen

-0.65

১

-0.60

১

-0.59

１

-0.59

 Fifteen

-0.56

 thirteen

-0.55

 Thirteen

-0.55

¹

-0.54

 sixteen

-0.53

POSITIVE LOGITS

 يتيمه

1.07

InjectAttribute

1.05

rungsseite

1.04

 gynhyrchwyd

0.89

Personensuche

0.88

AsUp

0.87

WithIOException

0.84

LookAnd

0.81

SharedCtor

0.80

 transfieras

0.80

Activations Density 0.944%

numbers and statistical values related to medical data

Negative numbers and arithmetic operations

numbers and symbols

No Comments

No Known Activations