INDEX

Explanations

programming syntax elements and various punctuations typically used in code

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

is followed by an article or adjective

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

-0.26

 retirer

-0.26

 aloj

-0.25

ūsu

-0.24

REMOVE

-0.24

 REMOVE

-0.23

 yhte

-0.23

一

-0.23

่ง

-0.23

Epoch

-0.23

POSITIVE LOGITS

OGND

1.08

 فريبيس

0.95

tanleria

0.89

 disambiguazione

0.88

 المعيارى

0.88

 snippetHide

0.87

Tembelea

0.83

extAlignment

0.82

 otomatig

0.82

 <>",

0.82

Activations Density 0.789%

programming syntax elements and various punctuations typically used in code

is followed by an article or adjective

No Comments

No Known Activations