INDEX

Explanations

references to "detuning" and related concepts in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

发表于

-0.44

 Wyman

-0.43

 Exactos

-0.43

TextInputLayout

-0.42

 UILabel

-0.40

MemoryWarning

-0.40

 Rigidbody

-0.39

Rigidbody

-0.38

flav

-0.38

 Edith

-0.38

POSITIVE LOGITS

 hurricane

0.73

 Hurricane

0.71

 toll

0.62

Hurricane

0.62

 initComponents

0.62

 ramp

0.60

 cyclone

0.59

 Colony

0.59

Colony

0.56

 hurricanes

0.55

Activations Density 0.297%

references to "detuning" and related concepts in scientific contexts

No Comments

No Known Activations