INDEX

Explanations

details related to living spaces and property features

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

preceding adjectives

np_acts-logits-general · gemini-2.0-flash

more than, also available

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 idéia

-1.11

 muß

-1.00

 skall

-1.00

 mußte

-0.92

 läßt

-0.88

 mußten

-0.84

 daß

-0.81

 müßte

-0.80

 !!!!!

-0.79

 !!!!!!

-0.78

POSITIVE LOGITS

Whilst

0.82

 cosy

0.81

(£

0.80

 instalment

0.80

 personalised

0.80

 Whilst

0.80

 recognisable

0.79

 prioritise

0.78

£

0.77

 personalisation

0.77

Activations Density 0.273%

details related to living spaces and property features

preceding adjectives

more than, also available

No Comments

No Known Activations