INDEX

Explanations

phrases and terms related to connections or relationships between entities

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

duality or pairs

np_acts-logits-general · gemini-2.0-flash

both, both, both, both

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

?,?,

-0.56

xyz

-0.38

bigoplus

-0.38

ifun

-0.38

Cuatro

-0.38

 allemaal

-0.37

all

-0.36

 varias

-0.35

 tres

-0.35

 Cuatro

-0.35

POSITIVE LOGITS

 beiden

2.23

 begge

2.22

 beide

2.16

 båda

2.16

 ambos

2.11

 Beide

2.09

 both

2.02

 entrambi

1.98

 Both

1.98

 beider

1.98

Activations Density 2.676%

phrases and terms related to connections or relationships between entities

duality or pairs

both, both, both, both

No Comments

No Known Activations