INDEX

Explanations

phrases that relate to limits and conditions of actions or states

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

as X as possible

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 kasarigan

-0.47

quiagem

-0.47

 otomatig

-0.41

 surla

-0.40

îtres

-0.40

 BoxDecoration

-0.39

 hochzeit

-0.38

Viited

-0.38

consulté

-0.37

brigens

-0.37

POSITIVE LOGITS

 possible

3.03

possible

2.61

 Possible

2.47

Possible

2.39

 posible

2.28

 possível

2.27

 POSSIBLE

2.19

 possibile

2.17

 posibles

2.03

 poffible

1.96

Activations Density 0.102%

phrases that relate to limits and conditions of actions or states

as X as possible

No Comments

No Known Activations