INDEX

Explanations

references to episode numbers in various contexts

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

raulic

-0.73

er

-0.71

 Erdoğan

-0.66

farin

-0.65

 papir

-0.63

nati

-0.62

ing

-0.61

CONSIN

-0.60

 للمعارف

-0.60

 Granger

-0.60

POSITIVE LOGITS

 episodes

1.44

 Episodes

1.41

episode

1.40

 episode

1.39

 Episode

1.37

 EPISODE

1.27

Episode

1.24

episodes

1.19

 épisode

1.19

Episodes

1.14

Activations Density 0.119%

references to episode numbers in various contexts

No Comments

No Known Activations