INDEX

Explanations

references to the term "host" in various contexts

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

 Jira

-0.78

 awakeFromNib

-0.74

McLaren

-0.71

 Gente

-0.70

 scio

-0.70

Wür

-0.69

 jurídica

-0.68

 Belleville

-0.67

StringField

-0.67

 Newberry

-0.66

POSITIVE LOGITS

 hosts

1.58

 HOST

1.52

 Hosts

1.50

 Host

1.48

 host

1.42

 hosting

1.39

Hosts

1.37

 Hosting

1.36

HOST

1.33

 hosted

1.27

Activations Density 0.047%

references to the term "host" in various contexts

No Comments

No Known Activations