INDEX

Explanations

mentions of doors and the actions associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ImageContext

-0.63

persky

-0.59

PerformLayout

-0.58

tvguidetime

-0.55

Gambas

-0.53

/**

-0.49

DeleteBehavior

-0.49

олові

-0.48

ământ

-0.48

Edge

-0.48

POSITIVE LOGITS

 door

2.32

 doors

1.93

door

1.78

 Door

1.75

 DOOR

1.73

Door

1.67

 puerta

1.56

 Doors

1.47

 doorway

1.45

doors

1.44

Activations Density 0.197%

mentions of doors and the actions associated with them

No Comments

No Known Activations