INDEX

Explanations

statements or questions about answers and inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 ModelRenderer

-0.46

complexType

-0.44

bower

-0.43

mtrl

-0.42

 gericht

-0.41

GEBURTS

-0.40

 Coimbra

-0.40

Kedves

-0.39

 vitara

-0.39

usercontent

-0.39

POSITIVE LOGITS

 typelib

0.79

OGND

0.75

脚注の使い方

0.73

httphttps

0.71

 EconPapers

0.69

OrBuilder

0.69

Cyfeiriadau

0.67

 answer

0.67

Tembelea

0.67

 समीक्षाओं

0.67

Activations Density 0.322%

statements or questions about answers and inquiries

No Comments

No Known Activations