INDEX

Explanations

phrases related to estimates or approximations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

рный

-0.56

resave

-0.54

 Faso

-0.53

NamedQueries

-0.53

 orice

-0.52

 propOrder

-0.52

ControllerAdvice

-0.52

writeField

-0.52

関連項目

-0.50

 Préférences

-0.49

POSITIVE LOGITS

 approximately

1.02

 approximate

0.92

 Approximately

0.92

approximately

0.85

Approximately

0.83

 Around

0.83

Cerca

0.82

 Approximate

0.81

 Cerca

0.80

 sekitar

0.79

Activations Density 0.174%

phrases related to estimates or approximations

No Comments

No Known Activations