INDEX

Explanations

references to lists and organizational structures

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

list items or variables

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

PostInfinity

-0.52

ViewImports

-0.49

原始内容存档于

-0.48

robe

-0.46

 समीक्षाएं

-0.45

+#+

-0.45

zoic

-0.44

ogno

-0.44

arangay

-0.43

 Issus

-0.43

POSITIVE LOGITS

httphttps

0.40

TagMode

0.38

errHandler

0.37

CloseOperation

0.34

 sides

0.33

ilg

0.32

 куда

0.32

別

0.31

bní

0.31

 ReSharper

0.30

Activations Density 0.027%

references to lists and organizational structures

list items or variables

No Comments

No Known Activations

references to lists and organizational structures

list items or variables

No Comments

No Known Activations