INDEX

Explanations

references to the concept of a "host" in various contexts

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

Following the word "host"

np_acts-logits-general · gemini-2.0-flash

host and its roles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 piacere

-0.74

 Jira

-0.65

 Esquire

-0.60

SSS

-0.59

 SwitchCompat

-0.59

idends

-0.58

 scio

-0.58

 StatelessWidget

-0.58

⮕

-0.58

ALR

-0.58

POSITIVE LOGITS

 hosts

1.16

 Host

1.12

 HOST

1.09

 Hosts

1.08

 host

1.07

 hosting

1.06

hos

1.05

 Hosting

1.03

HOST

0.99

Hos

0.99

Activations Density 0.078%

references to the concept of a "host" in various contexts

Following the word "host"

host and its roles

No Comments

No Known Activations