INDEX

Explanations

specific versions or references to the "Alpha" and "Beta" parameters in various contexts

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

"Alpha" prefix or term

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

</tr>

-0.40

 noOf

-0.39

er

-0.38

-0.37

for

-0.36

 تواند

-0.36

("~/

-0.36

to

-0.34

在

-0.34

POSITIVE LOGITS

 Alpha

2.09

Alpha

2.00

 ALPHA

1.83

 alpha

1.71

ALPHA

1.59

 ALPH

1.35

アルファ

1.32

 Alfa

1.30

alpha

1.27

Alfa

1.25

Activations Density 0.024%

specific versions or references to the "Alpha" and "Beta" parameters in various contexts

"Alpha" prefix or term

No Comments

No Known Activations