INDEX

Explanations

technical specifications and features of vehicles

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

followed by articles or prepositions

np_acts-logits-general · gemini-2.0-flash

pairs or multiples

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

 abstrato

-0.83

 fusca

-0.75

 avoient

-0.75

enumi

-0.74

+#+#

-0.74

 cauſe

-0.73

 preſent

-0.72

ſelf

-0.72

 houſe

-0.72

 ſche

-0.71

POSITIVE LOGITS

 dual

0.94

 double

0.80

 Dual

0.72

 triple

0.71

LED

0.70

 doble

0.69

dual

0.66

two

0.65

 adjustable

0.65

Activations Density 0.208%

technical specifications and features of vehicles

followed by articles or prepositions

pairs or multiples

No Comments

No Known Activations