INDEX

Explanations

specific acronyms and terms related to biological classifications and structures

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

 betweenstory

-0.71

RegistryLite

-0.45

 незавершена

-0.44

OGND

-0.43

 contextLoads

-0.42

༘

-0.41

бият

-0.41

setVerticalGroup

-0.41

LLocation

-0.40

bruno

-0.40

POSITIVE LOGITS

 Ба

1.54

Ba

1.54

BA

1.51

Ба

1.47

ba

1.45

Ba

1.45

BA

1.44

 ба

1.42

ба

1.33

Bac

1.26

Activations Density 0.358%

specific acronyms and terms related to biological classifications and structures

No Comments

No Known Activations