INDEX

Explanations

programming-related events and listener patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 uterine

-0.37

发表于

-0.37

Credit

-0.37

ConstraintMaker

-0.36

akang

-0.35

 Spare

-0.35

minton

-0.35

 Credit

-0.35

xrLabel

-0.34

eqref

-0.34

POSITIVE LOGITS

OnClickListener

1.10

ActionListener

1.02

Listener

0.96

 OnClickListener

0.93

 ActionListener

0.91

ChangeListener

0.88

listener

0.81

SuccessListener

0.79

WindowListener

0.79

CompleteListener

0.79

Activations Density 0.121%

programming-related events and listener patterns

No Comments

No Known Activations