INDEX

Explanations

code or code snippets.

oai_token-act-pair · gemini-2.0-flash

programming-related code statements

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

period/parenthesis

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

########.

-0.68

]")]

-0.66

PDOException

-0.60

 <=",

-0.60

//

-0.60

styleUrls

-0.57

bootstrapcdn

-0.56

XmlAccessorType

-0.56

 StatefulWidget

-0.56

twimg

-0.56

POSITIVE LOGITS

AndEndTag

0.62

RenderAtEndOf

0.53

 Exacts

0.50

 culturel

0.50

言い

0.50

org

0.49

finding

0.49

asm

0.48

Gut

0.48

com

0.47

Activations Density 0.582%

code or code snippets.

programming-related code statements

period/parenthesis

No Comments

No Known Activations