INDEX

Explanations

words used in informational, scientific, medical, and instructional contexts, sometimes with attention to specific substances, ingredients, or treatments such as OFF, topical corticosteroids and Nutella.

oai_token-act-pair · gemini-2.0-flash

Applying

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.66

StoryboardSegue

-0.64

UnsafeEnabled

-0.63

 snippetHide

-0.61

strix

-0.61

 Paglinawan

-0.59

TagMode

-0.59

Бахар

-0.57

цездатний

-0.57

érêt

-0.56

POSITIVE LOGITS

 application

1.88

 applied

1.76

 Application

1.73

 apply

1.72

 applying

1.71

application

1.67

Application

1.64

 Apply

1.58

applied

1.57

Apply

1.53

Activations Density 2.514%

words used in informational, scientific, medical, and instructional contexts, sometimes with attention to specific substances, ingredients, or treatments such as OFF, topical corticosteroids and Nutella.

Applying

No Comments

No Known Activations