INDEX

Explanations

words related to marketing or sales

oai_token-act-pair · gemini-2.0-flash

programming-related terms or code constructs

np_token-act-pair-logits · gpt-4o-mini

will

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

#+#

-0.54

RegressionTest

-0.45

 cavo

-0.42

™

-0.41

 inoxydable

-0.39

WebServlet

-0.39

obiety

-0.38

®

-0.37

AddRef

-0.37

kenalkan

-0.36

POSITIVE LOGITS

ViewImports

0.88

Tembelea

0.74

 <<<<<<<<<<<<<<

0.72

AndEndTag

0.70

makeConstraints

0.70

EDEFAULT

0.69

 doInBackground

0.65

tagHelperRunner

0.63

âtre

0.63

})`

0.62

Activations Density 36.923%

words related to marketing or sales

programming-related terms or code constructs

will

No Comments

No Known Activations