INDEX

Explanations

related to the significance or necessity of particular actions or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Sucesor

-0.54

}.

-0.52

 gynhyrchwyd

-0.49

 استنادى

-0.48

žka

-0.46

).

-0.46

IVEREF

-0.46

 varandra

-0.46

 mucho

-0.46

 pasal

-0.45

POSITIVE LOGITS

__":

0.64

InjectAttribute

0.63

 AssemblyTitle

0.59

fjspx

0.56

Πηγές

0.53

原始内容存档于

0.53

__':

0.53

QMetaType

0.53

romo

0.52

()]

0.51

Activations Density 0.438%

related to the significance or necessity of particular actions or concepts

No Comments

No Known Activations