INDEX

Explanations

acronyms and initialisms, particularly those related to computing and file formats

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

FR

-0.92

FE

-0.91

FA

-0.90

FE

-0.85

FA

-0.82

Fe

-0.81

Fe

-0.77

fe

-0.77

fe

-0.76

FR

-0.76

POSITIVE LOGITS

ConstraintMaker

0.77

CompilerServices

0.75

 ModelExpression

0.71

queryInterface

0.71

InitVars

0.69

writeFieldEnd

0.65

 تعدى

0.64

 scraper

0.63

principalColumn

0.63

SpringBootTest

0.62

Activations Density 4.840%

acronyms and initialisms, particularly those related to computing and file formats

No Comments

No Known Activations