INDEX

Explanations

keywords and phrases related to benefits and improvements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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



-0.63

 CascadeType

-0.59

]")]

-0.58

ThroughAttribute

-0.58

MemoryWarning

-0.57

 lest

-0.55

)$_

-0.55

<?

-0.55

 насељу

-0.53

)')

-0.53

POSITIVE LOGITS

 when

0.98

 dzięki

0.92

 grazie

0.88

 thanks

0.87

 grâce

0.84

 after

0.84

 gracias

0.83

 благодаря

0.82

 nhờ

0.76

ďaka

0.76

Activations Density 0.706%

keywords and phrases related to benefits and improvements

No Comments

No Known Activations