INDEX

Explanations

terms related to compatibility and support between systems and software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.98

Efq

-0.95

 Jefus

-0.94

PreExecute

-0.92

 ―――――

-0.91

 whoſe

-0.87

 ་་

-0.86

 Савезне

-0.86

MessageState

-0.84

 فريبيس

-0.83

POSITIVE LOGITS

 compatible

0.68

 compatibility

0.65

 compati

0.58

compatible

0.57

 compatibles

0.53

対応

0.53

uble

0.53

 Compatibility

0.51

compat

0.50

compatibility

0.49

Activations Density 0.373%

terms related to compatibility and support between systems and software

No Comments

No Known Activations