INDEX

Explanations

variables and indices used in iterative processes

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

loop indexing with i

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

posedge

-0.45

 يتيمه

-0.44

WebServlet

-0.42

gau

-0.41

complexType

-0.40

 ghost

-0.39

transQ

-0.39

 дописавши

-0.38

Olvid

-0.38

)}+

-0.37

POSITIVE LOGITS

 defaultstate

0.85

 GenerationType

0.59

 esternos

0.49

rungsseite

0.47

ñora

0.46

 noDo

0.46

tagext

0.46

pośred

0.46

AccessorTable

0.46

DNEY

0.45

Activations Density 0.006%

variables and indices used in iterative processes

loop indexing with i

No Comments

No Known Activations