INDEX

Explanations

terms related to API endpoints and their configurations

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

network and medical endpoints

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

🏼

-0.44

Geplaatst

-0.38

🏾

-0.38

marvin

-0.38

 Vás

-0.38

총

-0.36

Mis

-0.36

MathML

-0.35

 Murillo

-0.35

Skocz

-0.35

POSITIVE LOGITS

endpoint

1.31

 endpoint

1.30

 Endpoint

1.28

Endpoint

1.26

 endpoints

1.12

Endpoints

1.08

endpoints

1.05

ENDPOINT

1.02

endPoint

0.92

EndPoint

0.83

Activations Density 0.004%

terms related to API endpoints and their configurations

network and medical endpoints

No Comments

No Known Activations