INDEX

Explanations

phrases indicating potential or possibility

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

expressions indicating potential outcomes or possibilities

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

potential outcomes

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 spesso

-0.56

 Waray

-0.56

 menudo

-0.54

dafx

-0.53

står

-0.51

UserScript

-0.50

 frequentemente

-0.50

 stets

-0.48

 often

-0.48

meist

-0.48

POSITIVE LOGITS

 conceivably

1.13

 potentially

1.10

potentially

1.08

 potential

0.94

Potential

0.91

potential

0.90

 Potential

0.88

 feas

0.87

could

0.86

 potencial

0.85

Activations Density 0.073%

phrases indicating potential or possibility

expressions indicating potential outcomes or possibilities

potential outcomes

No Comments

No Known Activations