INDEX

Explanations

HTML and JavaScript code syntax related to navigating and organizing elements in a web page

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

HTML or code tags/attributes

np_acts-logits-general · gemini-2.0-flash

codes and punctuation following words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

twimg

-0.69

 SwitchCompat

-0.69

 umana

-0.69

getMenuInflater

-0.66

 سكانية

-0.64

 doInBackground

-0.62

 VIAF

-0.60

middels

-0.59

 geométrico

-0.58

+#+#

-0.57

POSITIVE LOGITS

andale

0.58

''

0.56

eabouts

0.56

'],$

0.53

ozat

0.52

`]

0.52

সং

0.51

 horri

0.50

omene

0.50

 Schles

0.50

Activations Density 0.461%

HTML and JavaScript code syntax related to navigating and organizing elements in a web page

HTML or code tags/attributes

codes and punctuation following words

No Comments

No Known Activations