INDEX

Explanations

words related to evaluating or ranking something

oai_token-act-pair · gemini-2.0-flash

assessment

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

eternal

-0.50

polation

-0.49

 prime

-0.49

 forms

-0.49

jugend

-0.48

 annual

-0.47

annual

-0.46

 tẩy

-0.46

rosi

-0.46

shutil

-0.45

POSITIVE LOGITS

 disambiguazione

1.02

ArgsConstructor

0.79

IntoConstraints

0.79

 pinulongan

0.68

 समीक्षक

0.67

 surla

0.66

 ModelExpression

0.66

 XCTest

0.65

 ligiloj

0.65

ArrowToggle

0.64

Activations Density 1.455%

words related to evaluating or ranking something

assessment

No Comments

No Known Activations