INDEX

Explanations

references to "pins" and their various contexts and uses

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

Revenir

-0.86

🤣🤣

-0.85

modelBuilder

-0.71

matchCondition

-0.70

 inflater

-0.69

tanleria

-0.69

oquia

-0.67

 sarung

-0.67

vių

-0.67

tencent

-0.67

POSITIVE LOGITS

 pins

1.70

Pin

1.68

pin

1.65

 Pins

1.64

PIN

1.54

Pin

1.53

pin

1.40

 pinning

1.37

 pinned

1.37

pins

1.36

Activations Density 0.156%

references to "pins" and their various contexts and uses

No Comments

No Known Activations