INDEX

Explanations

phrases that indicate changing conditions or statuses

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

preceding "change" or "changes"

np_acts-logits-general · gemini-2.0-flash

change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

providedIn

-0.82

DockStyle

-0.64

 Roskov

-0.58

+#+#

-0.55

حوالہ

-0.54

WebServlet

-0.52

getBounding

-0.51

kloped

-0.51

허

-0.50

Atsauces

-0.50

POSITIVE LOGITS

 change

3.36

change

2.92

 Change

2.90

Change

2.74

 changed

2.71

 CHANGE

2.66

 changes

2.64

 changing

2.59

CHANGE

2.47

 changement

2.34

Activations Density 0.800%

phrases that indicate changing conditions or statuses

preceding "change" or "changes"

change

No Comments

No Known Activations