INDEX

Explanations

URLs and links in the text

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

Web addresses (URLs)

np_acts-logits-general · gemini-2.0-flash

http and https links

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-0.99

IUrlHelper

-0.94

^(@)

-0.94

SharedDtor

-0.93

 Мексичка

-0.93

ⓧ

-0.88

]")]

-0.87

ContentAsync

-0.87

UnsafeEnabled

-0.87

 createContext

-0.86

POSITIVE LOGITS

↵↵

0.84

http

0.80

<eos>

0.76

 http

0.75

https

0.70

 https

0.69

↵↵↵↵

0.66

↵

0.59

↵↵↵↵↵

0.58

www

0.55

Activations Density 0.064%

URLs and links in the text

Web addresses (URLs)

http and https links

No Comments

No Known Activations