INDEX

Explanations

instances of the word "host" in various forms, indicating a focus on events and facilitation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 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

 kanilang

-0.67

 contu

-0.62

ształ

-0.62

TestingModule

-0.62

معلومات

-0.62

 kanyang

-0.61

ấn

-0.58

 restTemplate

-0.58

umb

-0.56

 /\.(

-0.56

POSITIVE LOGITS

 hosted

1.17

 hosting

1.03

 facilitated

0.98

 facilitating

0.97

 facilitation

0.91

 facilitate

0.89

 hosts

0.88

 Hosted

0.87

 Hosting

0.85

 facilitates

0.83

Activations Density 0.078%

instances of the word "host" in various forms, indicating a focus on events and facilitation

No Comments

No Known Activations