INDEX

Explanations

references to changes and their impacts in various contexts

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

"changes"

np_acts-logits-general · gemini-2.0-flash

changes

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 PriorityQueue

-0.39

autoComplete

-0.39

BindingResult

-0.38

guisement

-0.37

 desperate

-0.36

 Adler

-0.36

Contexts

-0.36

 onBind

-0.35

 poor

-0.35

PriorityQueue

-0.35

POSITIVE LOGITS

 changes

1.48

 Changes

1.48

Changes

1.48

changes

1.44

 CHANGES

1.30

 cambios

1.18

CHANGES

1.17

 change

1.16

 changements

1.16

 mudanças

1.13

Activations Density 0.428%

references to changes and their impacts in various contexts

"changes"

changes

No Comments

No Known Activations