INDEX

Explanations

inquiries related to features and suggestions in a context involving production or filmmaking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

jsxFileName

-0.60

ValueStyle

-0.47

 semula

-0.45

timmen

-0.44

 australis

-0.44

tagHelperRunner

-0.44

 alertDialog

-0.43

 robusta

-0.42

liesslich

-0.41

 internazionale

-0.41

POSITIVE LOGITS

or

0.87

 algún

0.84

 something

0.82

 someplace

0.78

awtextra

0.78

 somewhere

0.76

 algun

0.72

出版年

0.71

 irgende

0.71

 Something

0.69

Activations Density 0.644%

inquiries related to features and suggestions in a context involving production or filmmaking

No Comments

No Known Activations